INDEX

Explanations

phrases related to personal possessions and actions

oai_token-act-pair · gpt-3.5-turbo

possessive pronouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ĸļ

-0.87

drawn

-0.77

nil

-0.74

noon

-0.73

dding

-0.72

taker

-0.71

draw

-0.69

vine

-0.68

put

-0.68

quart

-0.68

POSITIVE LOGITS

 entire

1.43

 whole

1.01

own

0.88

 offending

0.86

selves

0.82

ãĥ³ãĤ¸

0.81

 entirety

0.80

 respective

0.78

 goods

0.78

 precious

0.76

Activations Density 0.365%

phrases related to personal possessions and actions

possessive pronouns

No Comments

No Known Activations