© 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
    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. 14465
    Prev
    Next
    INDEX
    Explanations

    verbs related to achieving a goal or completing a task successfully

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "accomplish" and its variations

    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
    creen
    -0.83
    option
    -0.75
     tyres
    -0.74
    lights
    -0.70
    olson
    -0.68
    north
    -0.65
    arth
    -0.65
    bane
    -0.63
    bah
    -0.63
    cube
    -0.63
    POSITIVE LOGITS
     accomplish
    1.15
     accomplished
    1.08
     accompl
    0.95
     accomplishment
    0.88
    ments
    0.84
    âĶģ
    0.80
     fruition
    0.80
    MENTS
    0.79
    ername
    0.78
    enance
    0.75
    Activations Density 0.007%

    No Known Activations