© 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. 2657
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a conclusion or summary

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of "all" or completeness

    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
    prus
    -0.72
    rive
    -0.69
    alyst
    -0.66
    ngth
    -0.66
    clock
    -0.66
    alks
    -0.65
    sequently
    -0.65
    ãģ®é
    -0.64
    aneers
    -0.64
    çīĪ
    -0.64
    POSITIVE LOGITS
    SPONSORED
    0.87
    soType
    0.82
     blasphemy
    0.68
     explan
    0.68
     understatement
    0.68
     scary
    0.66
     heresy
    0.65
    ï¸
    0.64
    natureconservancy
    0.64
     motivation
    0.63
    Activations Density 0.360%

    No Known Activations