© 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. 9-RES-JB
    11. 13175
    Prev
    Next
    INDEX
    Explanations

    instances of phrases containing the preposition "of" followed by a certain number of adjectives before a specific noun

    oai_token-act-pair · gpt-3.5-turbo

    references to "top-of-the-line" or high-quality items

    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
    mberg
    -0.65
    Mach
    -0.64
    incial
    -0.64
    witch
    -0.63
    PASS
    -0.63
    chell
    -0.61
    idan
    -0.58
     Rudd
    -0.58
     Luther
    -0.58
     DRAG
    -0.57
    POSITIVE LOGITS
     course
    0.75
    course
    0.71
    atre
    0.65
    vention
    0.64
     envelope
    0.63
    ventory
    0.63
     room
    0.62
    oscope
    0.62
     anecdote
    0.61
    ventions
    0.59
    Activations Density 0.078%

    No Known Activations