© 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. 3860
    Prev
    Next
    INDEX
    Explanations

    references to the concept of something having a limited or defined quantity

    oai_token-act-pair · gpt-3.5-turbo

    references to finite resources or constraints

    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
    ski
    -0.75
    lain
    -0.74
    mir
    -0.73
    AMI
    -0.73
    ership
    -0.72
    ogi
    -0.71
    obbies
    -0.70
    hin
    -0.69
    ific
    -0.68
    udic
    -0.67
    POSITIVE LOGITS
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.91
    ministic
    0.89
    ãĥ©ãĥ³
    0.71
     regress
    0.69
     capacitor
    0.68
    gger
    0.67
    ãĥ´
    0.66
     finite
    0.66
    itarian
    0.66
     bounded
    0.65
    Activations Density 0.021%

    No Known Activations