INDEX

Explanations

mentions of journalists

oai_token-act-pair · gpt-3.5-turbo

mentions of journalists and their experiences or conditions related to their work

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

inence

-0.76

oku

-0.74

ensions

-0.72

plan

-0.71

xual

-0.71

ministic

-0.69

BuyableInstoreAndOnline

-0.67

perm

-0.66

ples

-0.64

uras

-0.63

POSITIVE LOGITS

 Journalists

0.97

 journalists

0.95

 journalist

0.86

 Seymour

0.83

 corps

0.83

Journal

0.82

NPR

0.79

 covering

0.77

 laureate

0.76

 Journalism

0.75

Activations Density 0.028%

mentions of journalists

mentions of journalists and their experiences or conditions related to their work

No Comments

No Known Activations