INDEX

Explanations

proper nouns containing color descriptors

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "White."

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

udeau

-0.85

ITAL

-0.84

cffffcc

-0.82

ategory

-0.81

Downloadha

-0.79

yrinth

-0.75

odcast

-0.74

ension

-0.73

 WATCHED

-0.73

awaru

-0.73

POSITIVE LOGITS

caps

1.11

 supremacist

1.08

house

1.05

Sox

1.05

 supremacists

1.04

horse

1.02

berry

0.97

beard

0.95

bread

0.95

houses

0.94

Activations Density 0.029%

proper nouns containing color descriptors

occurrences of the word "White."

No Comments

No Known Activations