INDEX

Explanations

the word "sound"

oai_token-act-pair · gpt-3.5-turbo

references to auditory elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Lt

-0.70

MN

-0.69

olla

-0.69

WI

-0.68

stead

-0.67

²¾

-0.67

ierre

-0.67

icut

-0.67

lander

-0.67

xton

-0.66

POSITIVE LOGITS

interstitial

0.85

 Guatem

0.70

cher

0.68

 suspic

0.68

olation

0.64

liction

0.62

 Chilean

0.62

chers

0.62

 compilation

0.61

 honored

0.59

Activations Density 0.000%

the word "sound"

references to auditory elements

No Comments

No Known Activations