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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 8-RES-JB
    6. 20383
    Prev
    Next
    INDEX
    Explanations

    verbs related to continuation and persistence

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating ongoing actions or persistency in situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sponge
    -0.60
     stru
    -0.54
     smugg
    -0.54
    GMT
    -0.53
     Pir
    -0.51
     misunder
    -0.50
    arov
    -0.50
     Tsu
    -0.49
     juggling
    -0.49
     Torrent
    -0.49
    POSITIVE LOGITS
    nery
    0.79
     thereof
    0.78
    resent
    0.77
     thereafter
    0.77
     thereto
    0.73
    idge
    0.72
     theirs
    0.71
    sequent
    0.69
    morrow
    0.69
    qus
    0.67
    Activations Density 1.298%

    No Known Activations