© 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. 4502
    Prev
    Next
    INDEX
    Explanations

    phrases related to coordination and management

    oai_token-act-pair · gpt-3.5-turbo

    terms related to coordination and regulatory bodies

    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
    theless
    -0.80
    terday
    -0.78
     tune
    -0.77
     shroud
    -0.75
    olson
    -0.72
    使
    -0.68
    ä¸ī
    -0.68
    çĦ
    -0.67
     reserve
    -0.66
    ãģ«
    -0.66
    POSITIVE LOGITS
    abulary
    0.92
    idays
    0.84
    ifacts
    0.82
     Ago
    0.82
    oret
    0.81
    eworks
    0.79
    inct
    0.79
    orius
    0.79
    isan
    0.78
     Shots
    0.77
    Activations Density 0.127%

    No Known Activations