© 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. 20298
    Prev
    Next
    INDEX
    Explanations

    expressions related to hierarchical levels or rankings

    oai_token-act-pair · gpt-3.5-turbo

    classifications or rankings of entities and their associated tiers

    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
    ãĥŁ
    -0.68
    Leaks
    -0.68
    hoe
    -0.68
     videot
    -0.67
    Buzz
    -0.61
     bombard
    -0.59
     omission
    -0.59
     photoc
    -0.58
    Writer
    -0.57
    gif
    -0.57
    POSITIVE LOGITS
     standings
    0.79
     Rankings
    0.76
     Ranking
    0.74
     guiActiveUnfocused
    0.72
     tier
    0.71
     relegation
    0.70
    lishes
    0.69
     specialization
    0.68
     Membership
    0.67
    holders
    0.66
    Activations Density 1.191%

    No Known Activations