INDEX

Explanations

mentions of the word "Story"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Story" 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 @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

utive

-0.82

 stocking

-0.76

ktop

-0.75

ateurs

-0.75

etheless

-0.75

obe

-0.74

omin

-0.74

avorite

-0.74

uting

-0.74

omination

-0.73

POSITIVE LOGITS

 Story

1.28

telling

1.06

 Stories

1.05

Story

0.92

line

0.91

 Narr

0.91

 STORY

0.89

LIN

0.89

 Lines

0.86

lines

0.84

Activations Density 0.008%

mentions of the word "Story"

occurrences of the word "Story" in various contexts

No Comments

No Known Activations