INDEX

Explanations

references to the concept of "Self" or self-related terms

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "self" and its variations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

fred

-0.78

 amen

-0.74

oglu

-0.71

 Bethesda

-0.70

ollah

-0.68

phia

-0.67

Hos

-0.66

 Bolton

-0.64

sett

-0.63

ovan

-0.63

POSITIVE LOGITS

Self

3.62

 Self

2.69

 selfie

2.09

 self

2.03

self

1.93

 selfies

1.83

 selves

1.65

ELF

1.59

selves

1.43

 selfish

1.22

Activations Density 0.018%

references to the concept of "Self" or self-related terms

occurrences of the word "self" and its variations

No Comments

No Known Activations