INDEX

Explanations

phrases related to the term "Gaussian"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "Gaussian."

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

enance

-0.81

sburgh

-0.76

FACE

-0.76

gdala

-0.76

tenance

-0.72

ty

-0.72

PORT

-0.71

roleum

-0.71

tic

-0.70

ding

-0.68

POSITIVE LOGITS

Ga

1.13

ither

1.11

vernment

1.05

keye

1.03

pless

0.97

Ga

0.89

ussian

0.87

illard

0.85

uth

0.82

etz

0.81

Activations Density 0.013%

phrases related to the term "Gaussian"

occurrences of the term "Gaussian."

No Comments

No Known Activations