© 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. 0-RES-JB
    11. 4107
    Prev
    Next
    INDEX
    Explanations

    phrases related to achieving success or progress

    oai_token-act-pair · gpt-3.5-turbo

    references to monetary or tangible benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orah
    -0.72
    nr
    -0.66
    KA
    -0.64
     arranged
    -0.60
     Polic
    -0.59
    ordon
    -0.59
    onica
    -0.58
    Empty
    -0.57
     Noah
    -0.57
     Autism
    -0.57
    POSITIVE LOGITS
     gains
    3.76
     gain
    2.14
     gained
    1.65
    gain
    1.57
     losses
    1.55
     strides
    1.54
     advances
    1.53
     victories
    1.45
     Gain
    1.43
     profits
    1.42
    Activations Density 0.009%

    No Known Activations