INDEX

Explanations

phrases or contexts that express the idea of "degree" or "extent"

oai_token-act-pair · gpt-3.5-turbo

references to the degree or scope of a situation or phenomenon

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

Interstitial

-0.75

pton

-0.75

verbs

-0.73

ky

-0.68

 clay

-0.68

cair

-0.67

byte

-0.67

ker

-0.66

annon

-0.66

ivas

-0.65

POSITIVE LOGITS

 extent

0.93

 practicable

0.78

conom

0.78

essment

0.72

 amounts

0.71

ments

0.70

 casualties

0.69

es

0.66

 similarity

0.66

ibility

0.65

Activations Density 0.020%

phrases or contexts that express the idea of "degree" or "extent"

references to the degree or scope of a situation or phenomenon

No Comments

No Known Activations