INDEX

Explanations

references to uncertainties or speculations

oai_token-act-pair · gpt-3.5-turbo

references to the word "this" 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

istries

-0.79

anamo

-0.78

ãĤ¹ãĥĪ

-0.76

ands

-0.76

alties

-0.76

atoon

-0.74

phies

-0.73

idelines

-0.73

esm

-0.71

amia

-0.70

POSITIVE LOGITS

 trope

0.97

 happened

0.96

 happens

0.95

 arrangement

0.92

guy

0.90

 tactic

0.90

 discrepancy

0.89

 newfound

0.88

 phenomenon

0.88

 outcome

0.88

Activations Density 0.171%

references to uncertainties or speculations

references to the word "this" in various contexts

No Comments

No Known Activations