© 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. 6338
    Prev
    Next
    INDEX
    Explanations

    strings related to sequences or orders

    oai_token-act-pair · gpt-3.5-turbo

    references to sequences in general

    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
    ryn
    -0.86
    sburgh
    -0.84
    enthal
    -0.80
    lying
    -0.76
    young
    -0.76
    aghd
    -0.76
    vae
    -0.75
    wordpress
    -0.72
    aneers
    -0.71
    sle
    -0.71
    POSITIVE LOGITS
     Sequence
    1.08
     sequence
    1.04
     sequences
    0.98
     repeats
    0.81
     queues
    0.80
    ĸļ
    0.77
     sequencing
    0.75
    uality
    0.73
    alysis
    0.71
     unfold
    0.70
    Activations Density 0.012%

    No Known Activations