INDEX

Explanations

numerical values related to margins and errors

oai_token-act-pair · gpt-3.5-turbo

references to statistical margins of error

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

uni

-0.73

mine

-0.71

ibur

-0.70

oxide

-0.69

ergy

-0.68

abad

-0.66

JECT

-0.66

Uz

-0.64

der

-0.64

den

-0.62

POSITIVE LOGITS

 margin

1.08

 margins

1.01

 SHARES

0.85

 separating

0.76

margin

0.75

 favoring

0.74

irth

0.70

ageddon

0.69

acies

0.68

Skip

0.67

Activations Density 0.023%

numerical values related to margins and errors

references to statistical margins of error

No Comments

No Known Activations