INDEX

Explanations

edits or edited versions of text

oai_token-act-pair · gpt-3.5-turbo

instances of the word "edited" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

fall

-0.77

hood

-0.77

bley

-0.75

falls

-0.75

phal

-0.74

pton

-0.74

ptoms

-0.74

fw

-0.70

ãĤ©

-0.69

aches

-0.69

POSITIVE LOGITS

 summ

0.82

 excerpts

0.76

 editing

0.74

 transcript

0.73

 edits

0.73

 annex

0.72

orship

0.70

edited

0.69

 Delete

0.66

 edited

0.66

Activations Density 0.020%

edits or edited versions of text

instances of the word "edited" and its variations

No Comments

No Known Activations