INDEX

Explanations

technical terms related to software or product features

oai_token-act-pair · gpt-3.5-turbo

mentions of features and updates related to technology or software releases

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 accuses

-0.78

rique

-0.65

erity

-0.64

 accusing

-0.63

 blames

-0.63

 reckoning

-0.63

 blaming

-0.62

 Buchanan

-0.61

 Crane

-0.60

 Fairfax

-0.60

POSITIVE LOGITS

 included

0.91

mentioned

0.89

 incorporated

0.89

 Included

0.85

 additions

0.82

Introduced

0.82

 added

0.81

 implemented

0.81

 unlocked

0.81

 applicable

0.80

Activations Density 0.583%

technical terms related to software or product features

mentions of features and updates related to technology or software releases

No Known Activations