INDEX

Explanations

phrases related to investigation or examination

oai_token-act-pair · gpt-3.5-turbo

references to analysis and evaluation 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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ograp

-0.77

oiler

-0.73

ikan

-0.68

ocr

-0.64

addle

-0.63

pic

-0.62

iverse

-0.62

tick

-0.62

toggle

-0.61

oplan

-0.61

POSITIVE LOGITS

any

0.96

its

0.93

 subsequent

0.92

the

0.89

 other

0.88

 assorted

0.82

 others

0.80

 some

0.77

 those

0.75

 whichever

0.75

Activations Density 0.683%

phrases related to investigation or examination

references to analysis and evaluation in various contexts

No Comments

No Known Activations