© 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. 11-RES-JB
    11. 10098
    Prev
    Next
    INDEX
    Explanations

    locations and rankings among other entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the preposition "in" across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.87
    icer
    -0.75
    soever
    -0.74
    FIG
    -0.74
    bub
    -0.72
    iris
    -0.70
    thens
    -0.70
    raid
    -0.69
    stra
    -0.67
    wake
    -0.67
    POSITIVE LOGITS
     terms
    1.86
     popularity
    1.17
     regards
    1.16
     comparison
    1.06
     stature
    1.06
    efficiency
    1.01
     regard
    1.00
     sheer
    1.00
     attractiveness
    0.99
     prestige
    0.97
    Activations Density 0.160%

    No Known Activations