INDEX

Explanations

proper nouns, specifically related to names and locations

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Hazrat" and related variations

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

imates

-0.78

izers

-0.73

osaurs

-0.73

berus

-0.71

intendo

-0.71

istic

-0.71

ociation

-0.70

umbn

-0.69

umbers

-0.69

UCT

-0.68

POSITIVE LOGITS

mallow

0.86

wood

0.79

stack

0.77

boxes

0.76

leaf

0.75

hurst

0.73

ingly

0.72

 Hazel

0.69

storms

0.69

azel

0.69

Activations Density 0.020%

proper nouns, specifically related to names and locations

occurrences of the name "Hazrat" and related variations

No Comments

No Known Activations