INDEX

Explanations

words related to specific names, likely focusing on names with the letter "b" and "r"

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of individuals

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

pora

-0.66

 Siren

-0.65

anmar

-0.62

 Amen

-0.61

 disparate

-0.59

thirds

-0.58

 Eston

-0.58

appropriately

-0.58

 Azerbai

-0.57

bral

-0.57

POSITIVE LOGITS

estern

0.85

é¾

0.74

ichick

0.73

âĸ¬

0.71

lang

0.70

odon

0.69

onent

0.65

 Stard

0.65

furt

0.63

Activations Density 0.318%

words related to specific names, likely focusing on names with the letter "b" and "r"

proper nouns, specifically names of individuals

No Comments

No Known Activations