INDEX

Explanations

phrases related to limits and constraints

oai_token-act-pair · gpt-3.5-turbo

references to numerical limitations or thresholds

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

ublic

-0.85

rious

-0.76

vironment

-0.76

earth

-0.69

ALK

-0.66

namese

-0.66

lique

-0.66

nian

-0.65

TPP

-0.65

orthy

-0.64

POSITIVE LOGITS

 limits

0.97

 imposed

0.87

 limit

0.80

lessness

0.78

 amounts

0.78

 Limits

0.78

 amount

0.77

 restricts

0.75

 restriction

0.74

 tolerance

0.72

Activations Density 0.028%

phrases related to limits and constraints

references to numerical limitations or thresholds

No Comments

No Known Activations