© 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. 7-RES-JB
    11. 1949
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases related to criticism or analysis

    oai_token-act-pair · gpt-3.5-turbo

    statements highlighting significant issues or conditions affecting various aspects of society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     caution
    -0.75
    lique
    -0.74
    icularly
    -0.70
    lex
    -0.68
    ially
    -0.67
    avier
    -0.66
    gov
    -0.64
    itches
    -0.63
    maxwell
    -0.62
    nered
    -0.61
    POSITIVE LOGITS
     plag
    0.80
     underpin
    0.79
     heartbeat
    0.75
    ģĸ
    0.73
     surround
    0.70
     presently
    0.70
     accrued
    0.64
     hallmark
    0.64
    OPLE
    0.63
     afforded
    0.63
    Activations Density 0.268%

    No Known Activations