© 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. 7-RES-JB
    11. 11619
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "albeit" followed by associated concepts or details

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conditions, circumstances, or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     therein
    -0.71
     therefore
    -0.65
     accordingly
    -0.63
     (?,
    -0.59
     FTA
    -0.58
    bara
    -0.58
    orian
    -0.58
     Issa
    -0.57
    ETF
    -0.56
     meanwhile
    -0.56
    POSITIVE LOGITS
    cffffcc
    0.72
    interstitial
    0.69
    ãĥ©ãĥ³
    0.67
    vol
    0.67
    cial
    0.63
    Ô
    0.62
    ãĥĨãĤ£
    0.62
    cific
    0.60
     consideration
    0.60
    tained
    0.60
    Activations Density 0.273%

    No Known Activations