INDEX

Explanations

numerical expressions referring to a specific quantity

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "single" in various contexts

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

akings

-0.86

Downloadha

-0.83

apons

-0.76

raints

-0.73

 notor

-0.72

arium

-0.72

ooks

-0.72

acists

-0.69

enaries

-0.68

Hoo

-0.68

POSITIVE LOGITS

handedly

1.18

 digit

1.01

player

0.92

ton

0.91

 digits

0.87

 minute

0.86

digit

0.83

 sided

0.82

 parent

0.81

 molecule

0.79

Activations Density 0.017%

numerical expressions referring to a specific quantity

references to the concept of "single" in various contexts

No Comments

No Known Activations