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. 7-RES-JB
    6. 12787
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions or operations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating confusion or misunderstanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     neighb
    -0.82
     lifes
    -0.78
     ability
    -0.76
     probation
    -0.75
     wire
    -0.75
     prosec
    -0.74
     carriage
    -0.74
     waterfall
    -0.74
     negoti
    -0.73
     bid
    -0.71
    POSITIVE LOGITS
    Consider
    1.56
    Whether
    1.43
    Specifically
    1.39
    According
    1.39
    Advertisements
    1.38
    Indeed
    1.36
    Advertisement
    1.33
    For
    1.31
    Instead
    1.31
    Because
    1.30
    Activations Density 0.626%

    No Known Activations