INDEX

Explanations

phrases related to news articles or stories

oai_token-act-pair · gpt-3.5-turbo

repetitive mentions of the term "Story," indicating a focus on narrative or sequential content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

İĭ

-0.76

»Ĵ

-0.73

orpor

-0.70

ensor

-0.69

ibilities

-0.69

ergic

-0.68

vernment

-0.66

amily

-0.65

 sulph

-0.64

agles

-0.63

POSITIVE LOGITS

telling

1.17

line

0.88

 Story

0.84

bold

0.79

Maker

0.75

 Continued

0.75

 Transcript

0.75

stal

0.74

craft

0.74

hart

0.73

Activations Density 0.017%

phrases related to news articles or stories

repetitive mentions of the term "Story," indicating a focus on narrative or sequential content

No Comments

No Known Activations