Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 2820
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical actions involving force or movement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to powerful actions or strong intentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rosenberg
    -0.76
     Purg
    -0.73
     Gallup
    -0.72
     Bernstein
    -0.69
     Knox
    -0.68
     Instruments
    -0.67
    Gall
    -0.67
    igned
    -0.66
    iosity
    -0.66
     Assembly
    -0.66
    POSITIVE LOGITS
     swat
    2.27
    eme
    2.11
     waving
    1.44
     waved
    1.37
     Cout
    1.26
    ussie
    1.22
     chop
    1.16
     strand
    1.13
     chasing
    1.12
     Mb
    1.06
    Activations Density 0.029%

    No Known Activations