INDEX

Explanations

words related to the character Sherlock Holmes

oai_token-act-pair · gpt-3.5-turbo

references to Sherlock Holmes and related characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ital

-0.85

lag

-0.78

ersed

-0.78

ilater

-0.78

acid

-0.77

ciation

-0.75

ion

-0.75

resent

-0.71

tein

-0.71

ual

-0.71

POSITIVE LOGITS

 Holmes

1.23

atson

0.77

 Doyle

0.74

Lens

0.72

iday

0.70

XT

0.69

 Circus

0.67

 TAMADRA

0.66

MQ

0.66

INESS

0.64

Activations Density 0.069%

words related to the character Sherlock Holmes

references to Sherlock Holmes and related characters

No Comments

No Known Activations