© 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. 11202
    Prev
    Next
    INDEX
    Explanations

    assembled entities or objects

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "assembled" and related forms

    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
    tp
    -0.76
    eper
    -0.76
    mber
    -0.76
    thur
    -0.74
    ms
    -0.74
    ntax
    -0.73
    fet
    -0.72
    etheless
    -0.72
    TPS
    -0.71
    cas
    -0.69
    POSITIVE LOGITS
     assemble
    1.02
     assembled
    1.02
     assemb
    1.00
    ÃįÃį
    0.98
    eers
    0.96
     assembly
    0.93
     assembling
    0.91
     assemblies
    0.86
    escription
    0.80
    eering
    0.79
    Activations Density 0.010%

    No Known Activations