INDEX

Explanations

specific nouns preceded by the word "the"

oai_token-act-pair · gpt-3.5-turbo

phrases that relate to the concept of names and identification

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

venants

-0.72

agy

-0.71

efully

-0.70

imeo

-0.66

MRI

-0.66

heric

-0.65

issions

-0.65

phasis

-0.65

ashtra

-0.65

igue

-0.64

POSITIVE LOGITS

 Shots

0.72

 Uzbek

0.72

 suspects

0.71

 witnesses

0.69

 culprit

0.68

 Killer

0.66

 Mothers

0.64

 Jesus

0.63

Tup

0.61

 Ricky

0.61

Activations Density 0.088%

specific nouns preceded by the word "the"

phrases that relate to the concept of names and identification

No Comments

No Known Activations