Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 9162
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases or expressions that vividly depict a situation or scenario

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe or depict situations and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ERT
    -0.81
     overfl
    -0.70
    ktop
    -0.67
     replen
    -0.66
    requent
    -0.66
    staking
    -0.64
     ingestion
    -0.63
     digestion
    -0.63
    hops
    -0.63
    keep
    -0.62
    POSITIVE LOGITS
     picture
    0.81
     differently
    0.76
     landscape
    0.76
     likeness
    0.75
     mosaic
    0.74
     slate
    0.73
     vividly
    0.73
     caricature
    0.72
     landscapes
    0.72
     gloom
    0.71
    Activations Density 0.278%

    No Known Activations