© 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. 6-RES-JB
    11. 4154
    Prev
    Next
    INDEX
    Explanations

    phrases related to project phases or schedules

    oai_token-act-pair · gpt-3.5-turbo

    references to different phases in a process or project

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ILLE
    -0.91
    riad
    -0.91
    inately
    -0.85
    esome
    -0.80
     glim
    -0.78
    HCR
    -0.75
     Cosponsors
    -0.73
    intent
    -0.71
    ãĥ¤
    -0.70
     Rings
    -0.68
    POSITIVE LOGITS
     Phase
    0.88
     phase
    0.88
    hift
    0.85
     phases
    0.83
     stages
    0.76
    ISTER
    0.74
    arthed
    0.70
     transitions
    0.69
    itol
    0.69
    tenance
    0.68
    Activations Density 0.017%

    No Known Activations