INDEX

Explanations

terms related to recent events or developments, particularly those with a negative connotation like layoffs, closure, events, drama, scandal, and controversy

oai_token-act-pair · gpt-3.5-turbo

references to recent events and developments, particularly those involving changes or issues

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 someday

-0.84

 later

-0.81

later

-0.80

-0.79

-0.75

-0.74

-0.71

POSITIVE LOGITS

Reviewer

0.84

 developments

0.79

 revelations

0.78

shows

0.77

 proves

0.76

 confirms

0.76

 reveals

0.75

bernatorial

0.74

Enlarge

0.72

 controversies

0.70

Activations Density 0.274%

terms related to recent events or developments, particularly those with a negative connotation like layoffs, closure, events, drama, scandal, and controversy

references to recent events and developments, particularly those involving changes or issues

No Comments

No Known Activations