© 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. 0-RES-JB
    11. 19119
    Prev
    Next
    INDEX
    Explanations

    keywords related to assembling or building things

    oai_token-act-pair · gpt-3.5-turbo

    the concept of assembly in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Policy
    -0.64
    bit
    -0.63
    oral
    -0.63
    na
    -0.62
     Nid
    -0.61
     Trop
    -0.61
     Advertisement
    -0.60
    anasia
    -0.60
    allow
    -0.59
     karma
    -0.59
    POSITIVE LOGITS
     assembled
    3.89
     assemble
    2.79
     assembling
    2.38
    assembled
    2.09
     assemb
    1.93
     assembly
    1.66
     convened
    1.58
    semble
    1.53
    assembly
    1.52
    Assembly
    1.45
    Activations Density 0.010%

    No Known Activations