© 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. 2-RES-JB
    11. 8352
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "well"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "well," indicating a focus on evaluations or assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dash
    -0.67
    RAW
    -0.66
    ËĪ
    -0.66
     Harlem
    -0.64
     Madagascar
    -0.64
     surplus
    -0.63
    illary
    -0.60
     [+
    -0.60
    İĭ
    -0.59
     rash
    -0.59
    POSITIVE LOGITS
    esley
    1.23
    ness
    0.89
    oyd
    0.88
    ards
    0.88
    stones
    0.87
    espie
    0.84
    stone
    0.84
    ington
    0.84
    tenance
    0.81
    aday
    0.80
    Activations Density 0.008%

    No Known Activations