© 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. 4075
    Prev
    Next
    INDEX
    Explanations

    words related to negative events or obstacles

    oai_token-act-pair · gpt-3.5-turbo

    references to setbacks and failures

    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
    eous
    -0.68
    osc
    -0.66
    keys
    -0.66
    ie
    -0.64
    eton
    -0.63
     Nic
    -0.63
     EDIT
    -0.62
    ocom
    -0.62
    hes
    -0.61
    esi
    -0.61
    POSITIVE LOGITS
     setback
    3.76
     setbacks
    3.15
     defeat
    1.30
    inventoryQuantity
    1.24
     adversity
    1.24
     hardship
    1.19
     slump
    1.19
     drawback
    1.18
     blow
    1.15
     defeats
    1.14
    Activations Density 0.018%

    No Known Activations