INDEX

Explanations

mentions of specific universities, particularly UCLA and USC

oai_token-act-pair · gpt-3.5-turbo

references to UCLA and USC

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

odic

-0.85

BOOK

-0.83

ocene

-0.81

ãĥĥãĥĪ

-0.79

DonaldTrump

-0.77

ote

-0.76

rencies

-0.76

widget

-0.73

alez

-0.73

ulators

-0.72

POSITIVE LOGITS

 Bruins

1.05

 Extension

0.84

 UCLA

0.82

 Mutual

0.80

 ANGEL

0.77

ITY

0.77

ITED

0.74

 Pictures

0.73

 Graduate

0.71

UC

0.71

Activations Density 0.017%

mentions of specific universities, particularly UCLA and USC

references to UCLA and USC

No Comments

No Known Activations