© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 23615
    Prev
    Next
    INDEX
    Explanations

    complex sentences with a central idea or critical analysis expressed through approaching the sentence from various angles

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific symbol or character sequence, likely related to formatting or special indicators in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orts
    -0.75
    zel
    -0.67
    ŃĶ
    -0.65
    odo
    -0.64
    ©¶æ
    -0.63
    zza
    -0.62
    onds
    -0.62
    oby
    -0.61
    ¬¼
    -0.61
     deterior
    -0.61
    POSITIVE LOGITS
    perhaps
    1.14
    ––
    1.06
    meaning
    1.00
    something
    0.99
    âĢķ
    0.93
    but
    0.91
    âĢ¢âĢ¢
    0.91
    they
    0.89
    albeit
    0.89
     namely
    0.89
    Activations Density 0.219%

    No Known Activations