© 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. 7-RES-JB
    11. 13485
    Prev
    Next
    INDEX
    Explanations

    phrases related to support and impact

    oai_token-act-pair · gpt-3.5-turbo

    references to support and its impact on individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yz
    -0.78
    ynski
    -0.71
    ç«
    -0.69
    redits
    -0.68
    onet
    -0.67
    aith
    -0.66
    lesh
    -0.65
    waters
    -0.65
    razil
    -0.64
    odox
    -0.63
    POSITIVE LOGITS
     afforded
    0.90
     wrought
    0.86
     endured
    0.81
     entails
    0.81
     bestowed
    0.75
    FACE
    0.69
    enance
    0.68
     entail
    0.67
    arious
    0.65
     accrued
    0.64
    Activations Density 0.294%

    No Known Activations