INDEX

Explanations

verbs in imperative form

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate inevitability or necessity

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

IFrame

Link

Negative Logits

 srfAttach

-0.78

 sqor

-0.76

 Stain

-0.76

aucuses

-0.68

 Pupp

-0.62

achine

-0.62

antry

-0.62

 Timeline

-0.61

 Moose

-0.61

anova

-0.61

POSITIVE LOGITS

 reckoned

0.98

 seen

0.96

ige

0.90

 judged

0.89

 interpreted

0.84

 eaten

0.83

 viewed

0.83

 replaced

0.83

 borne

0.83

 done

0.82

Activations Density 0.063%

verbs in imperative form

phrases that indicate inevitability or necessity

No Known Activations