INDEX

Explanations

references to the NBC network

oai_token-act-pair · gpt-3.5-turbo

references to the NBC network

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

aunder

-0.76

rosse

-0.73

wikipedia

-0.72

itudinal

-0.72

antly

-0.71

piration

-0.71

andr

-0.71

cific

-0.70

erva

-0.70

arin

-0.70

POSITIVE LOGITS

Universal

1.25

SN

0.88

 News

0.85

NBC

0.83

WS

0.80

 affiliate

0.78

OH

0.77

 Broadcast

0.76

 Broadcasting

0.73

 Universal

0.73

Activations Density 0.011%

references to the NBC network

references to the NBC network

No Comments

No Known Activations