© 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. 1-RES-JB
    11. 9451
    Prev
    Next
    INDEX
    Explanations

    mentions of an entity or group named "ME"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Commodity Exchange (CME) Group

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inyl
    -0.74
    EStreamFrame
    -0.73
    nic
    -0.71
    raviolet
    -0.70
    kefeller
    -0.68
    tyard
    -0.68
    */(
    -0.66
    detail
    -0.65
    ogun
    -0.64
    paralle
    -0.64
    POSITIVE LOGITS
    ME
    1.06
    ETS
    0.99
    LL
    0.98
    ISTER
    0.90
    MENTS
    0.87
    zzo
    0.83
    PS
    0.83
    conom
    0.82
    ASE
    0.82
    AKING
    0.81
    Activations Density 0.005%

    No Known Activations