© 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. 18729
    Prev
    Next
    INDEX
    Explanations

    phrases related to moving away or leaving a situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a need to escape or remove oneself from a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Interstitial
    -0.93
    iances
    -0.69
    enium
    -0.66
    Must
    -0.63
     recip
    -0.63
    alian
    -0.61
    ounces
    -0.60
    Found
    -0.60
    ieth
    -0.60
    male
    -0.59
    POSITIVE LOGITS
     grips
    0.72
     Dodge
    0.69
    formed
    0.68
    jured
    0.66
     bounds
    0.66
     trouble
    0.65
    esville
    0.63
     bed
    0.63
    sein
    0.61
     Irma
    0.61
    Activations Density 0.047%

    No Known Activations