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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3980
    Prev
    Next
    INDEX
    Explanations

    HTML tags related to text formatting

    oai_token-act-pair · gpt-3.5-turbo

    tags or codes related to numerical specifications

    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
    mails
    -0.84
    ãģ®éŃĶ
    -0.82
    flies
    -0.80
    ãģķ
    -0.76
    女
    -0.75
    papers
    -0.75
    duction
    -0.75
    Ĥª
    -0.74
    tained
    -0.72
     reconc
    -0.72
    POSITIVE LOGITS
    ogether
    0.97
    imore
    0.90
    itle
    0.87
    itude
    0.83
    ucket
    0.83
    uner
    0.80
    oyd
    0.79
    ronics
    0.78
    itudinal
    0.77
    reet
    0.76
    Activations Density 0.017%

    No Known Activations