© 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. 2669
    Prev
    Next
    INDEX
    Explanations

    phrases related to intervention or taking action

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating intervention or involvement

    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
    omnia
    -0.73
    unct
    -0.66
     proceeds
    -0.65
     Mavericks
    -0.63
    wealth
    -0.62
    tumblr
    -0.60
     Consolid
    -0.58
    MAT
    -0.57
    summary
    -0.57
     Soc
    -0.57
    POSITIVE LOGITS
    circle
    0.79
    elight
    0.75
     Desk
    0.73
    frog
    0.72
    lights
    0.71
     bounds
    0.69
     fray
    0.69
     stride
    0.69
    arsh
    0.67
    adr
    0.67
    Activations Density 0.075%

    No Known Activations