Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-RES-JB
    6. 15528
    Prev
    Next
    INDEX
    Explanations

    words related to legal actions, specifically regarding being remanded or reprimanded

    oai_token-act-pair · gpt-3.5-turbo

    passive voice constructions, specifically the use of "remanded" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    saf
    -0.73
    INESS
    -0.73
    Article
    -0.67
    etta
    -0.65
    liest
    -0.63
    ched
    -0.62
    Chance
    -0.61
    pei
    -0.61
    è»
    -0.61
    ãĥ¼ãĥ«
    -0.61
    POSITIVE LOGITS
    anded
    1.58
    anding
    1.53
    ĸļ
    0.89
    ragon
    0.88
    ands
    0.84
    english
    0.84
    arity
    0.79
    ishly
    0.78
    lass
    0.78
    iple
    0.77
    Activations Density 0.010%

    No Known Activations