INDEX

Explanations

phrases related to podcasting

oai_token-act-pair · gpt-3.5-turbo

references to the term "pod"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ãĤ¤ãĥĪ

-0.74

ãĥ¼ãĥ³

-0.71

ãĤ¼ãĤ¦ãĤ¹

-0.68

FUL

-0.63

ãĤ´ãĥ³

-0.63

 REPORT

-0.63

 defic

-0.61

Ago

-0.61

listed

-0.61

ously

-0.59

POSITIVE LOGITS

iatric

1.15

esta

1.07

casters

1.05

bean

1.00

ols

0.98

caster

0.97

iat

0.92

imus

0.87

leton

0.85

lov

0.84

Activations Density 0.027%

phrases related to podcasting

references to the term "pod"

No Comments

No Known Activations