© 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. 4-RES-JB
    11. 10325
    Prev
    Next
    INDEX
    Explanations

    references to the word "Blood"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Blood" in various contexts

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

    No Comments

    Negative Logits
     srfAttach
    -0.91
    ×Ķ
    -0.81
    VICE
    -0.78
     Cheong
    -0.76
    acle
    -0.75
    OPLE
    -0.72
    DERR
    -0.72
    ALS
    -0.70
    ATIONS
    -0.69
    ________________________
    -0.69
    POSITIVE LOGITS
    hound
    1.13
    thirst
    1.12
     Pact
    1.06
    bath
    1.02
    stained
    1.01
    grave
    0.98
    metal
    0.90
    blood
    0.88
    shed
    0.87
    burn
    0.87
    Activations Density 0.013%

    No Known Activations