INDEX

Explanations

phrases related to a storyline continuation

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Story" indicating section headers or parts of a narrative

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

»Ĵ

-0.71

İĭ

-0.71

orpor

-0.70

ŃĶ

-0.68

onement

-0.67

ibles

-0.63

orporated

-0.62

anguage

-0.62

essage

-0.62

ibilities

-0.61

POSITIVE LOGITS

telling

1.14

bold

0.86

line

0.82

 Story

0.78

hart

0.78

stal

0.77

 Transcript

0.73

 Continued

0.73

views

0.72

makers

0.68

Activations Density 0.025%

phrases related to a storyline continuation

instances of the word "Story" indicating section headers or parts of a narrative

No Comments

No Known Activations