INDEX

Explanations

references to the mainstream media

oai_token-act-pair · gpt-3.5-turbo

references to mainstream media and its influence

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

cific

-0.81

atoon

-0.80

otos

-0.78

uana

-0.76

ursed

-0.76

arcity

-0.74

thur

-0.69

tein

-0.65

alid

-0.65

vag

-0.63

POSITIVE LOGITS

 mainstream

0.86

 outlets

0.81

 media

0.76

arily

0.76

ization

0.74

iary

0.72

ablishment

0.71

 establishment

0.70

 outlet

0.68

 circulation

0.68

Activations Density 0.026%

references to the mainstream media

references to mainstream media and its influence

No Comments

No Known Activations