INDEX

Explanations

words related to wax and candles

oai_token-act-pair · gpt-3.5-turbo

references to types of wax and candles

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

arity

-0.75

 Adin

-0.71

avez

-0.71

osuke

-0.67

HCR

-0.66

ICES

-0.66

ierrez

-0.65

ctica

-0.65

udder

-0.65

asio

-0.64

POSITIVE LOGITS

wax

1.04

Wax

0.89

es

0.84

lyr

0.83

manship

0.77

ed

0.76

\\\\\\\\

0.73

paper

0.72

ing

0.71

works

0.71

Activations Density 0.020%

words related to wax and candles

references to types of wax and candles

No Comments

No Known Activations