INDEX

Explanations

locations where people live or stay

oai_token-act-pair · gpt-3.5-turbo

references to places or locations associated with residences or living environments

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

maxwell

-0.86

ussian

-0.80

à¥

-0.72

olin

-0.71

ãģį

-0.71

aldi

-0.66

ãģĦ

-0.65

annot

-0.65

emonic

-0.65

ometric

-0.65

POSITIVE LOGITS

 located

0.96

 premises

0.94

tyard

0.90

 near

0.85

 precinct

0.82

 situated

0.80

 operated

0.79

 raided

0.78

 overlooking

0.77

 Complex

0.76

Activations Density 0.179%

locations where people live or stay

references to places or locations associated with residences or living environments

No Comments

No Known Activations