© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 23103
    Prev
    Next
    INDEX
    Explanations

    adjectives or phrases expressing positive or negative evaluation about specific topics

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and descriptors that convey positive or negative emotional connotations

    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
    akedown
    -0.69
    ahime
    -0.67
    oway
    -0.63
    inker
    -0.63
     Settlement
    -0.61
    Vert
    -0.58
     purse
    -0.58
     administrations
    -0.58
    onz
    -0.57
    ench
    -0.56
    POSITIVE LOGITS
     happening
    1.18
     about
    1.08
     ABOUT
    0.94
    worthy
    0.94
     happened
    0.89
     happen
    0.88
    ensical
    0.85
     happens
    0.84
    worldly
    0.84
    about
    0.84
    Activations Density 0.140%

    No Known Activations