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. 11-RES-JB
    6. 9742
    Prev
    Next
    INDEX
    Explanations

    words related to promoting or advertising something

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with promotional language or marketing

    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
    Ct
    -0.69
    ustration
    -0.66
    emort
    -0.66
    Pen
    -0.65
     reckoning
    -0.65
     pond
    -0.60
    alde
    -0.60
    bj
    -0.58
    Pg
    -0.58
    arf
    -0.57
    POSITIVE LOGITS
     virtues
    1.18
     successes
    0.87
     endorsements
    0.86
     superiority
    0.83
     stunts
    0.79
     benefits
    0.77
     praises
    0.77
     products
    0.77
     promises
    0.77
     credentials
    0.77
    Activations Density 0.206%

    No Known Activations