© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 6756
    Prev
    Next
    INDEX
    Explanations

    phrases related to bringing people or things together for a specific purpose

    oai_token-act-pair · gpt-3.5-turbo

    references to community involvement and connection among people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ende
    -0.76
    raid
    -0.71
    eme
    -0.64
    ording
    -0.63
    earcher
    -0.61
    Administ
    -0.60
    &&
    -0.59
    taker
    -0.58
    ©¶æ¥µ
    -0.58
    tein
    -0.57
    POSITIVE LOGITS
     onto
    1.13
     into
    1.12
     closer
    1.08
     forth
    1.03
     nearer
    0.99
     together
    0.94
     INTO
    0.88
     attention
    0.86
     back
    0.85
    into
    0.85
    Activations Density 0.152%

    No Known Activations