INDEX

Explanations

dates in a specific format

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Updated" likely indicating updates or revisions in content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

stood

-0.78

bors

-0.76

phal

-0.74

ften

-0.74

filled

-0.72

acht

-0.72

 pity

-0.71

aden

-0.70

ciplinary

-0.70

vo

-0.68

POSITIVE LOGITS

Updated

0.91

CLASSIFIED

0.88

Posted

0.80

 Updates

0.77

 Update

0.76

Published

0.72

UPDATE

0.71

Attempts

0.70

Update

0.70

ieval

0.70

Activations Density 0.007%

dates in a specific format

occurrences of the word "Updated" likely indicating updates or revisions in content

No Comments

No Known Activations