INDEX

Explanations

references to specific animals, particularly foxes

oai_token-act-pair · gpt-3.5-turbo

the word "fox" and variations of it within the text

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

assy

-0.74

 inval

-0.69

Definition

-0.65

apter

-0.65

 Pradesh

-0.63

 Edison

-0.63

rians

-0.63

atoon

-0.62

 Scotia

-0.62

rogens

-0.61

POSITIVE LOGITS

conn

1.34

es

0.96

hound

0.92

hair

0.91

holes

0.90

0.89

hole

0.87

haw

0.86

fox

0.85

worthy

0.85

Activations Density 0.016%

references to specific animals, particularly foxes

the word "fox" and variations of it within the text

No Comments

No Known Activations