INDEX

Explanations

mentions of the word "Mad" in various contexts and surroundings

oai_token-act-pair · gpt-3.5-turbo

references to the term "Mad" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

OPLE

-1.10

chnology

-1.04

 Vaugh

-0.85

kefeller

-0.80

oldown

-0.75

 sight

-0.74

çĦ

-0.73

×Ļ×

-0.73

lished

-0.72

uberty

-0.71

POSITIVE LOGITS

agascar

1.00

hya

0.97

ras

0.92

rid

0.91

eline

0.89

oka

0.85

Ã©n

0.84

onna

0.83

der

0.83

ness

0.81

Activations Density 0.008%

mentions of the word "Mad" in various contexts and surroundings

references to the term "Mad" in various contexts

No Comments

No Known Activations