INDEX

Explanations

words related to locations or proper nouns starting with "Mac"

oai_token-act-pair · gpt-3.5-turbo

references to specific individuals or proper nouns, particularly names related to the entertainment industry

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

 remnant

-0.65

agg

-0.63

warts

-0.62

 Kislyak

-0.60

 elig

-0.60

 hypert

-0.59

 buoy

-0.57

Kot

-0.57

 Boehner

-0.56

 biome

-0.56

POSITIVE LOGITS

arella

0.98

arie

0.93

amia

0.92

ESE

0.88

intosh

0.87

thur

0.84

sels

0.82

rules

0.77

wen

0.75

enzie

0.74

Activations Density 0.091%

words related to locations or proper nouns starting with "Mac"

references to specific individuals or proper nouns, particularly names related to the entertainment industry

No Comments

No Known Activations