INDEX

Explanations

proper nouns, specifically "Ga" followed by various different suffixes or words

oai_token-act-pair · gpt-3.5-turbo

references to the Gaussian distribution

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

enance

-0.80

FACE

-0.77

ty

-0.74

taking

-0.73

tenance

-0.72

PORT

-0.71

tic

-0.71

suit

-0.69

gdala

-0.68

sburgh

-0.67

POSITIVE LOGITS

Ga

1.16

ither

1.11

keye

1.05

vernment

1.03

Ga

0.97

pless

0.93

uth

0.88

illard

0.86

etz

0.84

ussian

0.83

Activations Density 0.012%

proper nouns, specifically "Ga" followed by various different suffixes or words

references to the Gaussian distribution

No Comments

No Known Activations