INDEX

Explanations

phrases related to legal actions or processes

oai_token-act-pair · gpt-3.5-turbo

punctuation marks signaling the end of sentences

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 blended

-0.82

 blending

-0.78

 glor

-0.75

 brilliantly

-0.75

 fashionable

-0.72

 resil

-0.72

 butcher

-0.71

 depreciation

-0.70

 thriving

-0.70

rys

-0.69

POSITIVE LOGITS

 Officials

1.22

 Sources

1.20

 Meanwhile

1.15

 Currently

1.15

 Otherwise

1.13

 Until

1.09

 According

1.07

If

1.07

 However

1.05

 Depending

1.04

Activations Density 0.397%

phrases related to legal actions or processes

punctuation marks signaling the end of sentences

No Comments

No Known Activations