INDEX

Explanations

phrases related to emotional reactions or attitudes

oai_token-act-pair · gpt-3.5-turbo

punctuation marks in written text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

itially

-0.74

ividual

-0.73

othal

-0.70

ozyg

-0.69

ogun

-0.69

uilt

-0.66

irlf

-0.66

;;;;;;;;;;;;

-0.65

ecause

-0.65

izont

-0.64

POSITIVE LOGITS

0.97

0.94

0.72

,...

0.70

CLASSIFIED

0.70

 antioxid

0.68

 behavi

0.66

 suscept

0.65

0.64

Activations Density 2.729%

phrases related to emotional reactions or attitudes

punctuation marks in written text

No Comments

No Known Activations