INDEX

Explanations

references to votes or ratings in the format number<tab>votes

oai_token-act-pair · gpt-3.5-turbo

numerical values related to votes or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

prises

-0.91

arte

-0.85

olicy

-0.81

alties

-0.80

liga

-0.79

oken

-0.79

ItemTracker

-0.79

anke

-0.79

prise

-0.75

eele

-0.74

POSITIVE LOGITS

0.89

th

0.86

0.82

0.81

ZI

0.79

0.76

0.74

0.72

TH

0.70

Activations Density 0.031%

references to votes or ratings in the format number<tab>votes

numerical values related to votes or statistics

No Comments

No Known Activations