INDEX

Explanations

symbols used as markers or separators

oai_token-act-pair · gpt-3.5-turbo

a specific character or symbol that appears frequently in the text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orts

-0.78

odcast

-0.72

ient

-0.71

pell

-0.70

lene

-0.67

pping

-0.66

ysis

-0.66

eks

-0.65

oyd

-0.65

pped

-0.64

POSITIVE LOGITS

––

1.25

————

0.83

âĸº

0.83

_-

0.75

Britain

0.71

————————————————

0.71

————————

0.71

Â£

0.71

_>

0.70

 Columb

0.69

Activations Density 0.103%

symbols used as markers or separators

a specific character or symbol that appears frequently in the text

No Comments

No Known Activations