INDEX

Explanations

words related to kissing

oai_token-act-pair · gpt-3.5-turbo

terms related to kissing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

é¾

-0.95

ulhu

-0.81

ifted

-0.79

irrel

-0.76

unc

-0.70

bably

-0.70

DoS

-0.69

heastern

-0.65

acco

-0.65

runs

-0.64

POSITIVE LOGITS

 kiss

1.37

 goodbye

1.24

 kisses

1.21

kiss

1.15

 kissing

1.13

 Kiss

1.11

creen

1.09

 kissed

1.07

 Goodbye

0.85

 farewell

0.82

Activations Density 0.007%

words related to kissing

terms related to kissing

No Comments

No Known Activations