© 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. 0-RES-JB
    6. 6629
    Prev
    Next
    INDEX
    Explanations

    phrases related to unsubscribing from services or unsubstantiated claims

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "unsub" or its variations, indicating a focus on subscription status or requests to unsubscribe

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iyah
    -0.71
    drivers
    -0.67
     tilt
    -0.67
     Guard
    -0.66
    brate
    -0.65
    GL
    -0.64
     mobility
    -0.63
    load
    -0.62
     Stud
    -0.62
    vantage
    -0.61
    POSITIVE LOGITS
     unsub
    4.29
     unfounded
    1.82
     baseless
    1.62
     unanswered
    1.33
     untrue
    1.28
     debunked
    1.23
     discredited
    1.08
     miscon
    1.07
     unsupported
    1.07
     spurious
    1.05
    Activations Density 0.024%

    No Known Activations