INDEX

Explanations

phrases where something or someone is described as the top priority or best in a category

oai_token-act-pair · gpt-3.5-turbo

references to a top priority or ranking

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

onics

-0.78

ages

-0.76

rad

-0.74

athered

-0.73

Adams

-0.73

 Spaces

-0.70

ories

-0.69

alg

-0.69

areth

-0.69

ifi

-0.69

POSITIVE LOGITS

 contender

0.96

 loader

0.79

 spot

0.78

 trending

0.76

 priority

0.76

 offender

0.76

 antagonist

0.74

 inhibitor

0.70

 gorilla

0.69

 generator

0.69

Activations Density 0.027%

phrases where something or someone is described as the top priority or best in a category

references to a top priority or ranking

No Comments

No Known Activations