INDEX

Explanations

different forms of the word "heard."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "heard" 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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

PHOTOS

-0.80

ahime

-0.71

ila

-0.69

igsaw

-0.68

tan

-0.66

isoft

-0.65

eros

-0.65

illian

-0.64

ãĤ¦

-0.63

istration

-0.60

POSITIVE LOGITS

 voices

1.20

 whispers

1.01

 confessions

1.01

 rumours

0.98

 rumors

0.97

 noises

0.96

 footsteps

0.93

 loud

0.92

 anecd

0.90

 louder

0.89

Activations Density 0.048%

different forms of the word "heard."

occurrences of the word "heard" and its variations

No Comments

No Known Activations