© 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. 3-RES-JB
    6. 2850
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to names or locations

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Titan" or similar sounding words and phrases, particularly in a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bered
    -0.75
    ategory
    -0.69
    agents
    -0.64
     Dise
    -0.64
     entrants
    -0.61
    pressure
    -0.61
    PRES
    -0.60
    Sean
    -0.60
    oney
    -0.59
    ¥µ
    -0.59
    POSITIVE LOGITS
    itan
    1.09
    ica
    1.06
    igans
    0.92
    osaurs
    0.92
    ic
    0.91
    fall
    0.88
    ienne
    0.88
    arium
    0.84
    ics
    0.84
    ical
    0.81
    Activations Density 0.006%

    No Known Activations