INDEX

Explanations

the word "leg" followed by a number

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "leg" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

âķĲâķĲ

-0.64

 canv

-0.63

ktop

-0.61

 polar

-0.60

tery

-0.58

 Moderate

-0.58

bern

-0.58

 selecting

-0.57

 Petraeus

-0.57

AAP

-0.56

POSITIVE LOGITS

isl

1.20

itimate

1.19

acies

1.08

acy

1.02

rett

0.96

edly

0.94

iev

0.93

uin

0.92

enic

0.92

ends

0.91

Activations Density 0.008%

the word "leg" followed by a number

occurrences of the term "leg" and its variations

No Comments

No Known Activations