INDEX

Explanations

questions or requests for information

oai_token-act-pair · gpt-3.5-turbo

instances of the word "asked" and its variants in various contexts

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

 Confeder

-0.74

 limbs

-0.64

 convergence

-0.62

Est

-0.62

Sham

-0.61

auer

-0.61

 Cock

-0.59

Bay

-0.59

herence

-0.58

 Cheong

-0.57

POSITIVE LOGITS

 asked

0.85

 rhet

0.82

 questions

0.80

naires

0.78

 repeatedly

0.77

naire

0.74

 posed

0.72

 asking

0.72

ĸļ

0.72

 questioned

0.72

Activations Density 0.035%

questions or requests for information

instances of the word "asked" and its variants in various contexts

No Comments

No Known Activations