INDEX

Explanations

mentions of the television network HBO

oai_token-act-pair · gpt-3.5-turbo

mentions of HBO and its related content or shows

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

acular

-0.88

acle

-0.85

omaly

-0.83

uation

-0.82

alion

-0.74

uart

-0.72

forms

-0.70

ivated

-0.70

igned

-0.70

jury

-0.70

POSITIVE LOGITS

HBO

0.87

TV

0.87

 Wire

0.86

 Networks

0.82

 Films

0.82

EW

0.82

ÃįÃį

0.77

 Television

0.75

 Studios

0.75

 premiered

0.74

Activations Density 0.019%

mentions of the television network HBO

mentions of HBO and its related content or shows

No Comments

No Known Activations