INDEX

Explanations

words related to medals, particularly bronze, silver, and gold

oai_token-act-pair · gpt-3.5-turbo

references to medals in competitive contexts, particularly in sports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

rir

-0.82

 Stras

-0.71

BOOK

-0.65

iannopoulos

-0.65

mosp

-0.65

hetto

-0.64

eu

-0.64

 PLAN

-0.63

ther

-0.62

clave

-0.60

POSITIVE LOGITS

 medal

1.11

 medals

1.02

 Medal

0.97

inal

0.83

animous

0.82

ists

0.81

 Medals

0.80

icum

0.78

ificent

0.78

 captcha

0.77

Activations Density 0.017%

words related to medals, particularly bronze, silver, and gold

references to medals in competitive contexts, particularly in sports

No Comments

No Known Activations