© 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. 0-RES-JB
    11. 6674
    Prev
    Next
    INDEX
    Explanations

    words related to the process of consolidating or merging something into a unified whole

    oai_token-act-pair · gpt-3.5-turbo

    terms related to consolidation and midterm events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rings
    -0.76
     Rings
    -0.72
    inent
    -0.71
     jew
    -0.71
     hats
    -0.70
    jew
    -0.69
     referees
    -0.69
    CHAT
    -0.68
     bows
    -0.67
     Jew
    -0.67
    POSITIVE LOGITS
     consolidation
    2.08
     consolid
    1.82
     consolidate
    1.61
     Drupal
    1.57
    ÅĤ
    1.47
     consolidated
    1.41
    rupal
    1.30
     Consolid
    1.28
     Accountability
    1.23
     midterm
    1.23
    Activations Density 0.052%

    No Known Activations