© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 18085
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce a subsequent explanation or elaboration

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "for" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥīãĥ©
    -0.79
    chenko
    -0.75
    urat
    -0.74
    inished
    -0.69
    quartered
    -0.66
    oried
    -0.66
    soever
    -0.65
    urgical
    -0.63
    âĶĢ
    -0.63
    ettel
    -0.63
    POSITIVE LOGITS
     starters
    1.49
    give
    1.24
    got
    1.17
    gettable
    1.14
     sake
    1.07
    getting
    1.06
    bidden
    1.03
    gotten
    1.01
    cing
    1.01
     instance
    0.97
    Activations Density 0.154%

    No Known Activations