INDEX

Explanations

comparisons or contrasts involving people or groups

oai_token-act-pair · gpt-3.5-turbo

the word "like" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

arbon

-0.93

iven

-0.78

VERTISEMENT

-0.72

ourse

-0.71

ells

-0.71

 indic

-0.69

 simul

-0.69

ysical

-0.68

ipple

-0.68

atform

-0.68

POSITIVE LOGITS

lihood

1.13

lier

0.98

 Erik

0.93

 Pamela

0.92

 Mike

0.87

 Philippe

0.85

 Eric

0.85

 yours

0.84

Ian

0.83

 Sergio

0.81

Activations Density 0.087%

comparisons or contrasts involving people or groups

the word "like" in various contexts

No Comments

No Known Activations