© 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. 18467
    Prev
    Next
    INDEX
    Explanations

    text snippets related to being at the top of a ranking or hierarchy

    oai_token-act-pair · gpt-3.5-turbo

    prepositions indicating ranking or position

    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
    ary
    -0.70
    eral
    -0.67
    Cause
    -0.64
    ista
    -0.61
    PsyNetMessage
    -0.60
    iment
    -0.60
    mere
    -0.59
     embodiments
    -0.58
     Ruk
    -0.58
    gans
    -0.58
    POSITIVE LOGITS
     hill
    0.85
     charts
    0.82
     heap
    0.82
     notch
    0.80
     earners
    0.77
     stairs
    0.76
     nowhere
    0.75
     standings
    0.74
     drawer
    0.72
     PAGE
    0.70
    Activations Density 0.068%

    No Known Activations