© 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. 8-RES-JB
    11. 6540
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing opinions or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to self-reflection and decision-making

    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
    Adds
    -0.65
     Downing
    -0.64
    Loading
    -0.61
     Lub
    -0.60
     Corpor
    -0.59
     Drunk
    -0.58
     Logan
    -0.57
     Franco
    -0.57
    major
    -0.57
    Berry
    -0.57
    POSITIVE LOGITS
    iety
    0.80
     hereafter
    0.78
     aspire
    0.77
    abouts
    0.74
    yssey
    0.74
    catentry
    0.72
    posium
    0.70
     thereafter
    0.70
     thereof
    0.69
    artney
    0.68
    Activations Density 0.339%

    No Known Activations