INDEX

Explanations

terms related to family relationships, especially uncles and aunts

oai_token-act-pair · gpt-3.5-turbo

references to familial relationships, specifically uncles and aunts

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

mberg

-0.82

isers

-0.76

mith

-0.64

âĹ¼

-0.64

isation

-0.63

rd

-0.62

izers

-0.62

 collapse

-0.61

istically

-0.61

Effect

-0.61

POSITIVE LOGITS

aned

0.93

 Vernon

0.92

liest

0.92

 uncle

0.89

Tup

0.89

heses

0.81

athy

0.80

 nephew

0.78

lies

0.77

anny

0.77

Activations Density 0.040%

terms related to family relationships, especially uncles and aunts

references to familial relationships, specifically uncles and aunts

No Comments

No Known Activations