INDEX

Explanations

words related to residing or living in a place

oai_token-act-pair · gpt-3.5-turbo

terms related to living beings or populations in a given environment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

heet

-0.87

ripp

-0.85

enic

-0.81

clone

-0.77

MED

-0.76

jer

-0.72

enegger

-0.72

printed

-0.71

ray

-0.69

hiba

-0.69

POSITIVE LOGITS

 inhabit

0.95

 inhab

0.94

 dwell

0.94

 inhabited

0.88

 dwelling

0.88

 inhabitants

0.86

dw

0.79

 dwellings

0.76

verning

0.75

 Dwell

0.75

Activations Density 0.014%

words related to residing or living in a place

terms related to living beings or populations in a given environment

No Comments

No Known Activations