© 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. 8-RES-JB
    11. 17046
    Prev
    Next
    INDEX
    Explanations

    phrases related to movement or change in direction

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "back" and its variations, relating to themes of movement or return

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    merce
    -0.82
    »Ĵ
    -0.76
    inas
    -0.75
    oin
    -0.66
    Plot
    -0.64
    illon
    -0.63
    PF
    -0.63
    MON
    -0.62
    inery
    -0.62
    rano
    -0.62
    POSITIVE LOGITS
     forth
    0.94
    arching
    0.80
    puff
    0.72
    forth
    0.71
     Forth
    0.67
     curtain
    0.64
     whence
    0.63
    )=(
    0.62
    umbered
    0.62
     haunt
    0.61
    Activations Density 0.133%

    No Known Activations