© 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. 9-RES-JB
    6. 16317
    Prev
    Next
    INDEX
    Explanations

    specific days mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Today" signaling updates or announcements

    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
    76561
    -0.72
    onne
    -0.67
    ogly
    -0.63
    acci
    -0.63
    --------------------------------------------------------
    -0.61
    este
    -0.61
    unta
    -0.60
     "$:/
    -0.59
    haul
    -0.58
    aughed
    -0.58
    POSITIVE LOGITS
     marks
    1.02
     we
    0.86
     marked
    0.83
    adays
    0.82
    's
    0.80
     afternoon
    0.76
     morning
    0.73
     corresponds
    0.69
     brings
    0.68
    bush
    0.68
    Activations Density 0.087%

    No Known Activations