© 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. 23437
    Prev
    Next
    INDEX
    Explanations

    phrases related to the aftermath or continuation of an event

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "after" followed by a numerical value

    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
     constitu
    -0.73
    女
    -0.73
    opsis
    -0.72
    aez
    -0.71
    enf
    -0.70
    eous
    -0.68
    ements
    -0.65
    oho
    -0.64
    orio
    -0.64
    IFIED
    -0.63
    POSITIVE LOGITS
    noon
    0.98
     completing
    0.94
     retiring
    0.92
     finishing
    0.89
     exiting
    0.83
    wards
    0.83
     undergoing
    0.82
     defeating
    0.80
     acquiring
    0.80
     losing
    0.80
    Activations Density 0.097%

    No Known Activations