© 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. 10-RES-JB
    11. 6611
    Prev
    Next
    INDEX
    Explanations

    phrases related to conducting surveys or polls

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to polling and survey data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.68
    DragonMagazine
    -0.60
     Kislyak
    -0.59
    plates
    -0.58
     glance
    -0.57
    bush
    -0.57
    agine
    -0.55
    gio
    -0.54
     rods
    -0.54
    RAY
    -0.54
    POSITIVE LOGITS
     Radiant
    0.68
    ailability
    0.66
    aditional
    0.63
    Þ
    0.61
     pione
    0.60
    inguished
    0.58
    registered
    0.56
    ippery
    0.55
     adherent
    0.54
    ippy
    0.53
    Activations Density 0.136%

    No Known Activations