© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 15675
    Prev
    Next
    INDEX
    Explanations

    terms related to sequencing, such as "Sequences" and "Sequencing"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sequencing and sequences

    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
    ModLoader
    -0.90
    hips
    -0.82
    fman
    -0.73
    aneers
    -0.73
    rieg
    -0.73
    dom
    -0.71
    road
    -0.71
    ryn
    -0.70
    habi
    -0.70
    landish
    -0.70
    POSITIVE LOGITS
    enced
    0.91
     Sequence
    0.84
    encing
    0.77
    entially
    0.76
    encer
    0.76
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.75
     Sequ
    0.74
     sequence
    0.70
    urally
    0.68
     DNA
    0.67
    Activations Density 0.074%

    No Known Activations