INDEX

Explanations

numbers related to numerical rankings or measurements

oai_token-act-pair · gpt-3.5-turbo

references to the number 35 and its various contexts or implications

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

prises

-0.71

 Payton

-0.70

hare

-0.70

nesday

-0.66

ifiable

-0.65

urred

-0.65

prise

-0.65

hran

-0.64

imaru

-0.63

enance

-0.63

POSITIVE LOGITS

1.38

rd

0.84

mm

0.79

th

0.79

Â°

0.78

ACP

0.74

MM

0.74

%-

0.72

Activations Density 0.086%

numbers related to numerical rankings or measurements

references to the number 35 and its various contexts or implications

No Comments

No Known Activations