INDEX

Explanations

mentions of reporters in different contexts, such as interviews, press conferences, and events

oai_token-act-pair · gpt-3.5-turbo

references to reporters or journalism

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ality

-0.63

imal

-0.61

 Loving

-0.61

avour

-0.60

ave

-0.58

mite

-0.58

 Device

-0.58

é¾įåĸļå£«

-0.57

odus

-0.56

 amulet

-0.56

POSITIVE LOGITS

 reporters

3.44

 journalists

2.76

 reporter

2.16

 Journalists

1.95

 photographers

1.84

 journalist

1.70

 analysts

1.64

 staffers

1.61

 editors

1.59

 bloggers

1.59

Activations Density 0.017%

mentions of reporters in different contexts, such as interviews, press conferences, and events

references to reporters or journalism

No Comments

No Known Activations