© 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. 2-RES-JB
    11. 23508
    Prev
    Next
    INDEX
    Explanations

    words related to blood vessels and circulation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to veins and arteries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    %]
    -0.72
    Gy
    -0.71
    Ħ¢
    -0.70
    Policy
    -0.67
    fixed
    -0.67
    flo
    -0.66
    âĺħâĺħ
    -0.65
    ommod
    -0.65
    ————
    -0.64
    MAT
    -0.64
    POSITIVE LOGITS
     vein
    1.39
     veins
    1.17
     artery
    0.85
    ril
    0.82
     arteries
    0.81
    phrine
    0.80
    akra
    0.77
    ectomy
    0.77
    itial
    0.76
    marks
    0.76
    Activations Density 0.014%

    No Known Activations