INDEX

Explanations

phrases related to the concept of applying rules or principles to different scenarios

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate applicability or relevance to various subjects or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

erd

-0.93

heit

-0.81

ight

-0.76

iev

-0.71

FORMATION

-0.71

icter

-0.71

ikk

-0.69

achev

-0.69

ipedia

-0.69

inus

-0.68

POSITIVE LOGITS

 every

0.97

 everyone

0.92

 other

0.89

all

0.89

 EVERY

0.89

 virtually

0.88

 everything

0.88

 everybody

0.87

 many

0.84

ALL

0.82

Activations Density 0.205%

phrases related to the concept of applying rules or principles to different scenarios

phrases that indicate applicability or relevance to various subjects or situations

No Comments

No Known Activations