INDEX

Explanations

proper nouns and names related to political figures or entities

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Ste" and related terms

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

etheless

-0.81

 eleph

-0.77

IFIED

-0.71

OUNT

-0.69

nas

-0.68

Kod

-0.64

ieu

-0.63

oral

-0.62

gdala

-0.61

tan

-0.61

POSITIVE LOGITS

chnology

1.06

ampunk

1.02

pping

1.02

uben

1.01

xton

0.94

ering

0.91

pped

0.90

ffen

0.90

alth

0.89

aling

0.88

Activations Density 0.026%

proper nouns and names related to political figures or entities

occurrences of the name "Ste" and related terms

No Comments

No Known Activations