© 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. 10-RES-JB
    11. 10766
    Prev
    Next
    INDEX
    Explanations

    technical coding characters and symbols related to programming languages

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the forward slash character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Moody
    -0.70
     Pepsi
    -0.69
     tender
    -0.69
     soaring
    -0.67
     tighter
    -0.67
     vaguely
    -0.67
     relentlessly
    -0.67
     bubble
    -0.66
     cle
    -0.66
     aspir
    -0.65
    POSITIVE LOGITS
    \/\/
    1.51
    ËĪ
    1.27
    usr
    1.26
    Film
    1.15
    ********************************
    1.13
    wcsstore
    1.13
    uploads
    1.12
    pol
    1.09
    Applications
    1.06
    Library
    1.06
    Activations Density 0.015%

    No Known Activations