INDEX

Explanations

references to objects or concepts related to lockers

oai_token-act-pair · gpt-3.5-turbo

terms related to specific locations and classifications within a structured environment

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

DEN

-0.88

entry

-0.78

emin

-0.75

©¶æ¥µ

-0.74

ered

-0.72

ı

-0.68

ĺħ

-0.67

ĩ

-0.67

senal

-0.66

Ł

-0.65

POSITIVE LOGITS

ocker

1.20

artney

0.81

obby

0.77

acus

0.76

obyl

0.75

udder

0.74

apter

0.70

asper

0.69

oos

0.69

oaded

0.68

Activations Density 0.026%

references to objects or concepts related to lockers

terms related to specific locations and classifications within a structured environment

No Comments

No Known Activations