© 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. 11-RES-JB
    11. 17233
    Prev
    Next
    INDEX
    Explanations

    phrases indicating speculation or objective statements about various subjects

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "seems to" and variations indicating perception or opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opens
    -0.85
    ãĤ¦ãĤ¹
    -0.69
    cart
    -0.68
    uates
    -0.65
     begins
    -0.65
     Ends
    -0.62
     opens
    -0.61
    ridden
    -0.61
    POST
    -0.61
    quished
    -0.60
    POSITIVE LOGITS
     be
    1.39
     specialize
    1.24
     despise
    1.22
     prefer
    1.18
     have
    1.15
     dislike
    1.15
     know
    1.13
     possess
    1.10
     want
    1.09
     enjoy
    1.09
    Activations Density 0.194%

    No Known Activations