INDEX

Explanations

mentions of following or joining actions

oai_token-act-pair · gpt-3.5-turbo

phrases and terms related to events and follow-ups in narratives

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

 maxim

-0.77

 optim

-0.71

 lull

-0.71

ilt

-0.70

insk

-0.69

ilts

-0.66

 deterior

-0.66

ient

-0.65

 simpl

-0.65

 ruins

-0.65

POSITIVE LOGITS

 Previously

0.80

ANI

0.73

 Eleven

0.71

omore

0.70

 Nieto

0.69

zona

0.68

 namely

0.68

nine

0.66

Hart

0.65

 Previous

0.64

Activations Density 0.454%

mentions of following or joining actions

phrases and terms related to events and follow-ups in narratives

No Comments

No Known Activations

mentions of following or joining actions

phrases and terms related to events and follow-ups in narratives

No Comments

No Known Activations