INDEX

Explanations

phrases related to specific standards or requirements that need to be met

oai_token-act-pair · gpt-3.5-turbo

references to criteria and standards

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

orld

-0.79

vironment

-0.76

joy

-0.75

resent

-0.71

sky

-0.70

icago

-0.68

ntil

-0.67

lar

-0.66

TPP

-0.65

Leary

-0.65

POSITIVE LOGITS

 criteria

1.29

 criterion

0.98

erion

0.92

 cutoff

0.87

 thresholds

0.84

 definitions

0.72

 threshold

0.72

 dictates

0.70

ifiers

0.70

 guidelines

0.69

Activations Density 0.020%

phrases related to specific standards or requirements that need to be met

references to criteria and standards

No Comments

No Known Activations