INDEX

Explanations

unexpected or surprising events or developments

oai_token-act-pair · gpt-3.5-turbo

references to unexpected changes or turns in narrative or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

pta

-0.77

ufact

-0.76

ogl

-0.73

 Ducks

-0.69

 Domain

-0.66

encia

-0.64

och

-0.63

inez

-0.61

arel

-0.61

EXP

-0.61

POSITIVE LOGITS

 twist

1.20

 twists

1.05

abouts

0.84

 Twist

0.80

 angle

0.77

 twisted

0.76

 Whedon

0.75

hered

0.74

angle

0.74

 endings

0.73

Activations Density 0.081%

unexpected or surprising events or developments

references to unexpected changes or turns in narrative or situations

No Comments

No Known Activations