© 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. 2478
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ————————————————
    -0.70
    mate
    -0.70
    mates
    -0.67
    forward
    -0.67
    stand
    -0.66
    mont
    -0.64
     Pop
    -0.64
    ================================
    -0.63
    çIJ
    -0.63
    Cro
    -0.61
    POSITIVE LOGITS
    avorite
    0.84
    orem
    0.77
     warr
    0.66
    apest
    0.66
    retty
    0.63
    obook
    0.62
    uristic
    0.61
    arnaev
    0.61
     feas
    0.60
    avored
    0.60
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.