INDEX

Explanations

mentions of family members such as uncles

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "uncle" and its variants in relation to family dynamics

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

mberg

-0.87

istas

-0.75

isers

-0.68

isation

-0.63

veyard

-0.62

izu

-0.62

EVA

-0.62

 lapse

-0.62

ization

-0.61

acters

-0.59

POSITIVE LOGITS

 uncle

1.04

hest

0.95

liest

0.88

ired

0.87

aned

0.85

 aunt

0.84

rieved

0.83

 niece

0.82

 nephew

0.82

 Uncle

0.81

Activations Density 0.017%

mentions of family members such as uncles

occurrences of the word "uncle" and its variants in relation to family dynamics

No Comments

No Known Activations