© 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. 20185
    Prev
    Next
    INDEX
    Explanations

    terms related to interference, disruption, and conflict

    oai_token-act-pair · gpt-3.5-turbo

    references to chaos or disorder in various contexts

    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
     Canaver
    -0.79
     Collider
    -0.66
    terday
    -0.63
    achu
    -0.63
     Logo
    -0.63
    NAS
    -0.60
    ursday
    -0.59
     Daytona
    -0.58
     Evolution
    -0.58
    hene
    -0.58
    POSITIVE LOGITS
    their
    0.98
     theirs
    0.92
     themselves
    0.87
     their
    0.82
    Their
    0.78
     they
    0.76
     discreet
    0.75
    they
    0.74
     bribes
    0.72
     undet
    0.71
    Activations Density 1.556%

    No Known Activations