INDEX

Explanations

proper nouns related to people, primarily focusing on the name "Seth."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Seth."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sight

-0.72

 vain

-0.72

give

-0.69

 subp

-0.67

sighted

-0.67

vis

-0.65

patient

-0.65

secut

-0.64

respons

-0.64

breeding

-0.63

POSITIVE LOGITS

 Seth

1.18

 Rollins

0.93

lings

0.83

nikov

0.75

 Guth

0.74

Ö¼

0.73

lehem

0.72

nan

0.72

imal

0.71

aceae

0.71

Activations Density 0.006%

proper nouns related to people, primarily focusing on the name "Seth."

occurrences of the name "Seth."

No Comments

No Known Activations