INDEX

Explanations

mentions of journalists or correspondents

oai_token-act-pair · gpt-3.5-turbo

mentions of correspondents in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

perm

-0.72

Ice

-0.70

Da

-0.70

formation

-0.69

Struct

-0.66

bra

-0.65

argon

-0.65

err

-0.64

ouses

-0.63

eat

-0.63

POSITIVE LOGITS

 correspondent

1.49

 journalist

0.96

 reporter

0.90

 Correspond

0.88

ially

0.84

 laureate

0.83

 camer

0.80

 writer

0.80

 photographer

0.77

 Fellow

0.77

Activations Density 0.006%

mentions of journalists or correspondents

mentions of correspondents in various contexts

No Comments

No Known Activations