© 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. 20142
    Prev
    Next
    INDEX
    Explanations

    phrases related to hypothetical scenarios and potential outcomes

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements indicating potential outcomes or consequences

    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
     Annotations
    -0.64
    LESS
    -0.63
     envy
    -0.60
     contrasts
    -0.60
    ictionary
    -0.59
    Afee
    -0.59
     amazed
    -0.59
    ighters
    -0.59
    ;;;;;;;;
    -0.58
     cu
    -0.57
    POSITIVE LOGITS
     tomorrow
    1.05
     someday
    0.92
     succeeds
    0.81
     succeed
    0.79
     hereafter
    0.67
     tonight
    0.66
     sufficiently
    0.66
     Maiden
    0.65
     prevail
    0.64
     BALL
    0.62
    Activations Density 0.308%

    No Known Activations