© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 20719
    Prev
    Next
    INDEX
    Explanations

    references to the abbreviation "NH"

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations and associated entities, particularly pertaining to New Hampshire

    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
    notations
    -0.75
    module
    -0.74
    cial
    -0.72
    grading
    -0.69
    ments
    -0.69
    wards
    -0.68
    letters
    -0.68
    aic
    -0.66
    Letter
    -0.66
     pains
    -0.66
    POSITIVE LOGITS
    NH
    1.26
     NH
    1.18
    JD
    0.80
    OH
    0.76
    ADRA
    0.75
    eree
    0.74
    UFC
    0.74
    IJ
    0.73
    aiman
    0.72
     NJ
    0.72
    Activations Density 0.009%

    No Known Activations