INDEX

Explanations

locations or positions relative to other objects in a physical space

oai_token-act-pair · gpt-3.5-turbo

locations and physical objects within various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Slot

-0.61

ħĭ

-0.60

 Committees

-0.59

aution

-0.59

BM

-0.58

 Puzz

-0.57

Prop

-0.57

 Cosponsors

-0.57

SB

-0.56

wcsstore

-0.56

POSITIVE LOGITS

(~

0.83

isphere

0.78

ifice

0.68

enium

0.68

oyer

0.67

ele

0.64

INE

0.61

clock

0.60

isle

0.60

 where

0.60

Activations Density 0.290%

locations or positions relative to other objects in a physical space

locations and physical objects within various contexts

No Comments

No Known Activations