© 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. 18561
    Prev
    Next
    INDEX
    Explanations

    verbs related to the completion or outcome of an action

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "end up" and its variations

    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
    itsch
    -0.67
     Advisory
    -0.59
     announcer
    -0.59
     backdrop
    -0.56
     acidic
    -0.55
    esis
    -0.55
     advisory
    -0.54
    Pal
    -0.53
    pload
    -0.53
     Leader
    -0.52
    POSITIVE LOGITS
    angering
    1.20
    owment
    1.00
    ebted
    1.00
    orse
    0.96
    ocrin
    0.93
    orses
    0.92
    angers
    0.88
    eared
    0.87
    ear
    0.86
     abruptly
    0.85
    Activations Density 0.053%

    No Known Activations