© 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. 8-RES-JB
    11. 20271
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by a form of the verb "to say"

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals making statements or comments

    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
    Reviewer
    -0.83
    finder
    -0.75
    geries
    -0.72
    uploads
    -0.71
    ocyte
    -0.68
     Craigslist
    -0.66
    iencies
    -0.65
     Parenthood
    -0.65
    isite
    -0.65
    Torrent
    -0.65
    POSITIVE LOGITS
     reiterated
    1.38
     remarks
    1.29
     spoke
    1.25
     reiter
    1.23
     reiterate
    1.21
     stressed
    1.20
     clarified
    1.20
     quoted
    1.19
     emphas
    1.19
     praised
    1.19
    Activations Density 0.669%

    No Known Activations