INDEX

Explanations

mentions of 'sheet'

oai_token-act-pair · gpt-3.5-turbo

references to "sheet" and related materials or concepts

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

Interstitial

-0.81

 Advocate

-0.80

ilee

-0.78

ourke

-0.72

 Valley

-0.70

qua

-0.69

Pacific

-0.69

 Abbey

-0.68

essee

-0.66

=-=-=-=-=-=-=-=-

-0.63

POSITIVE LOGITS

sheet

1.40

sheets

1.20

 sheet

1.05

 sheets

1.04

enium

0.82

paper

0.80

 Sheet

0.77

meal

0.77

mination

0.76

heet

0.75

Activations Density 0.020%

mentions of 'sheet'

references to "sheet" and related materials or concepts

No Comments

No Known Activations