© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 23864
    Prev
    Next
    INDEX
    Explanations

    phrases related to evaluations or judgments expressed in the past tense

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be" in various tenses

    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
     dismant
    -0.68
     SPD
    -0.67
     Vers
    -0.67
     millenn
    -0.66
     juven
    -0.66
     Techn
    -0.65
     pursu
    -0.63
     Notting
    -0.63
     predicate
    -0.62
     Sapp
    -0.61
    POSITIVE LOGITS
    tics
    0.96
    Ĥİ
    0.90
    rael
    0.89
     guiActiveUnfocused
    0.87
    ws
    0.87
    senal
    0.86
    abella
    0.82
    hots
    0.81
    chery
    0.81
    alde
    0.79
    Activations Density 0.549%

    No Known Activations