© 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. 7-RES-JB
    11. 7181
    Prev
    Next
    INDEX
    Explanations

    terms related to accessibility and user-friendliness

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lees
    -1.02
    stones
    -0.98
    ateurs
    -0.93
    tags
    -0.87
    tracks
    -0.87
    classes
    -0.86
    Ps
    -0.86
    laws
    -0.86
    ernels
    -0.85
    Nazis
    -0.84
    POSITIVE LOGITS
     version
    1.14
     affair
    1.04
     standpoint
    1.00
     perspective
    1.00
     solution
    0.97
     environment
    0.95
     relationship
    0.94
     situation
    0.93
     approach
    0.93
     scenario
    0.90
    Activations Density 0.416%

    No Known Activations