INDEX

Explanations

mentions of a specific word starting with "Kw" in English or other languages

oai_token-act-pair · gpt-3.5-turbo

proper nouns and names, particularly related to people and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

riages

-0.79

rative

-0.78

qa

-0.77

rar

-0.76

hematically

-0.73

ual

-0.73

lies

-0.72

rador

-0.72

ula

-0.72

rette

-0.70

POSITIVE LOGITS

DER

0.71

itionally

0.71

atts

0.67

ONG

0.64

versions

0.62

 Dickens

0.61

kers

0.61

ution

0.61

 succession

0.60

esi

0.60

Activations Density 0.100%

mentions of a specific word starting with "Kw" in English or other languages

proper nouns and names, particularly related to people and places

No Comments

No Known Activations