INDEX

Explanations

dates or references to specific events

oai_token-act-pair · gpt-3.5-turbo

references to significant events or issues from the previous year

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

 fuss

-0.73

 streaks

-0.65

ratulations

-0.64

 Malays

-0.62

STEM

-0.60

 goose

-0.60

 spores

-0.59

ptoms

-0.59

 coherent

-0.58

 vividly

-0.57

POSITIVE LOGITS

 behest

1.11

 expense

0.89

 altar

0.88

 headquarters

0.83

 helm

0.79

 intersections

0.78

 doorstep

0.78

Aren

0.78

 checkpoint

0.75

itent

0.74

Activations Density 0.663%

dates or references to specific events

references to significant events or issues from the previous year

No Comments

No Known Activations