INDEX

Explanations

specific numbers or identifiers embedded in text

oai_token-act-pair · gpt-3.5-turbo

numerical references, especially related to statistics or data points

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

achus

-0.92

 tradem

-0.87

ktop

-0.82

 millenn

-0.78

car

-0.75

holders

-0.73

¥µ

-0.71

¥ŀ

-0.70

ller

-0.70

cle

-0.69

POSITIVE LOGITS

rd

0.91

0.83

 ILCS

0.81

0.80

0.78

arians

0.78

awks

0.76

iance

0.74

ancouver

0.74

ESS

0.73

Activations Density 0.070%

specific numbers or identifiers embedded in text

numerical references, especially related to statistics or data points

No Comments

No Known Activations