INDEX

Explanations

proper names, particularly the name "Randy"

oai_token-act-pair · gpt-3.5-turbo

mentions of specific people and names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

strings

-0.85

pmwiki

-0.82

ivity

-0.78

ioch

-0.76

oresc

-0.72

orescence

-0.71

unction

-0.70

odic

-0.69

sf

-0.68

student

-0.67

POSITIVE LOGITS

 Cout

0.94

 Randy

0.90

 Olson

0.87

 Gregory

0.86

 Savage

0.85

 Curtis

0.83

 Bauer

0.82

 McMahon

0.80

 Hendricks

0.78

 Axel

0.77

Activations Density 0.007%

proper names, particularly the name "Randy"

mentions of specific people and names

No Comments

No Known Activations