INDEX

Explanations

mentions of political figures, especially negative references and critiques

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "and."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

inarily

-0.76

ridges

-0.68

note

-0.67

Contents

-0.65

culus

-0.65

floor

-0.65

physical

-0.64

different

-0.64

IED

-0.64

ENS

-0.63

POSITIVE LOGITS

 Associates

0.90

 vice

0.83

 others

0.77

ERSON

0.76

 Sons

0.74

 associates

0.73

 assorted

0.71

 consequently

0.69

 other

0.69

 then

0.68

Activations Density 0.336%

mentions of political figures, especially negative references and critiques

occurrences of the word "and."

No Comments

No Known Activations