© 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. 6-RES-JB
    11. 19681
    Prev
    Next
    INDEX
    Explanations

    names that end with "ner"

    oai_token-act-pair · gpt-3.5-turbo

    the term "ner," indicating a focus on entities or individuals associated with that suffix

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.69
    urities
    -0.66
    avorite
    -0.65
    EMP
    -0.64
    oral
    -0.63
     Occupations
    -0.63
    UTC
    -0.63
     runaway
    -0.61
     VIDE
    -0.58
    UV
    -0.58
    POSITIVE LOGITS
    getic
    1.05
    ding
    1.01
    gie
    0.93
    ger
    0.88
    ning
    0.86
    idge
    0.86
    stein
    0.85
    nen
    0.85
    lund
    0.84
    sonian
    0.84
    Activations Density 0.024%

    No Known Activations