INDEX

Explanations

phrases related to limits and boundaries

oai_token-act-pair · gpt-3.5-turbo

mentions of restrictions or boundaries

oai_token-act-pair · gpt-4o-mini Triggered 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

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ublic

-0.82

rious

-0.79

nian

-0.70

ALK

-0.69

earth

-0.69

vironment

-0.68

alky

-0.66

PE

-0.65

FORE

-0.64

TPP

-0.63

POSITIVE LOGITS

 limits

0.94

 restraints

0.76

 imposed

0.75

 restricts

0.75

lessness

0.74

 Limits

0.74

 limit

0.74

 amount

0.72

 amounts

0.72

 restriction

0.71

Activations Density 0.023%

phrases related to limits and boundaries

mentions of restrictions or boundaries

No Comments

No Known Activations