Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 3632
    Prev
    Next
    INDEX
    Explanations

    descriptions of people and their actions

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to social justice and inequality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]).
    -0.63
    SPONSORED
    -0.59
    >]
    -0.57
    Gene
    -0.57
    Auth
    -0.57
    ]),
    -0.56
    arthed
    -0.55
    })
    -0.54
    Ħ¢
    -0.54
    Last
    -0.53
    POSITIVE LOGITS
     however
    0.54
     flatt
    0.54
     though
    0.53
     everywhere
    0.50
     meanwhile
    0.49
    ometimes
    0.47
     insofar
    0.47
     ital
    0.47
     orphans
    0.47
     subdiv
    0.46
    Activations Density 2.100%

    No Known Activations