INDEX

Explanations

mentions of unexpected plot twists in textual content

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "twist" 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 @ 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

league

-0.74

ufact

-0.64

 Ducks

-0.64

hammad

-0.63

inately

-0.63

Male

-0.63

particip

-0.62

rahim

-0.62

asking

-0.61

estine

-0.61

POSITIVE LOGITS

 twist

1.24

 twists

1.14

 Twist

0.91

 endings

0.84

 twisting

0.83

 Whedon

0.75

stroke

0.73

 weave

0.73

abouts

0.72

 bend

0.72

Activations Density 0.014%

mentions of unexpected plot twists in textual content

occurrences of the word "twist" in various contexts

No Comments

No Known Activations