INDEX

Explanations

terms related to spitting or spitting actions

oai_token-act-pair · gpt-3.5-turbo

actions related to spitting and its variations

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

Reviewer

-0.76

 facult

-0.71

é¾įå

-0.65

å§«

-0.65

clinton

-0.65

SEC

-0.64

undai

-0.63

FINE

-0.63

 Passage

-0.62

HCR

-0.62

POSITIVE LOGITS

ting

0.93

 spit

0.89

balls

0.87

ball

0.81

ters

0.81

 spew

0.80

 spat

0.74

fires

0.73

ted

0.70

 spray

0.70

Activations Density 0.023%

terms related to spitting or spitting actions

actions related to spitting and its variations

No Comments

No Known Activations