INDEX

Explanations

mentions of people's residences or living situations

oai_token-act-pair · gpt-3.5-turbo

instances of the word "lives" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

sonian

-0.71

ociated

-0.68

xual

-0.66

phabet

-0.66

ractive

-0.65

roe

-0.64

orically

-0.64

ession

-0.64

Applic

-0.64

essee

-0.63

POSITIVE LOGITS

lihood

0.84

chool

0.79

stead

0.74

blog

0.74

 Forever

0.73

 abroad

0.71

rio

0.71

 Juliet

0.70

vic

0.69

 ashore

0.69

Activations Density 0.019%

mentions of people's residences or living situations

instances of the word "lives" in various contexts

No Comments

No Known Activations