© 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. 7723
    Prev
    Next
    INDEX
    Explanations

    words related to cognitive abilities

    oai_token-act-pair · gpt-3.5-turbo

    mention of cognitive abilities and associated concepts

    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
    wives
    -0.84
    EGA
    -0.76
    encer
    -0.71
    FORE
    -0.71
    arov
    -0.69
    olicited
    -0.67
     Mex
    -0.66
    Bey
    -0.66
    andro
    -0.65
     Khe
    -0.65
    POSITIVE LOGITS
     disson
    1.48
     enh
    1.07
     impairment
    1.00
     faculties
    0.99
     behavioural
    0.92
     enhancement
    0.89
     behavi
    0.84
    Ħ¢
    0.82
     impair
    0.81
     enhancing
    0.81
    Activations Density 0.032%

    No Known Activations