INDEX

Explanations

the word "Wolf"

oai_token-act-pair · gpt-3.5-turbo

references to the word "Wolf" or its variations

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

bably

-0.88

pora

-0.76

thritis

-0.76

acists

-0.75

nces

-0.73

perture

-0.73

ursed

-0.72

acterial

-0.71

ngth

-0.71

 conflic

-0.69

POSITIVE LOGITS

enstein

1.33

hound

1.25

sburg

1.06

gang

1.02

 Wolf

1.01

Wolf

0.99

 Wolves

0.98

pack

0.96

owitz

0.96

rider

0.94

Activations Density 0.018%

the word "Wolf"

references to the word "Wolf" or its variations

No Comments

No Known Activations