INDEX

Explanations

names or entities with the substring "lar"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Lar" 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 @ 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

manship

-0.97

CRIP

-0.90

ãģ®éŃĶ

-0.87

éĹĺ

-0.83

ä»£

-0.72

å£«

-0.71

EY

-0.70

 Samoa

-0.70

ħĭ

-0.66

ORGE

-0.65

POSITIVE LOGITS

vae

1.04

issa

0.93

bage

0.88

acy

0.88

sson

0.88

acial

0.86

ocious

0.86

abee

0.84

una

0.82

imore

0.81

Activations Density 0.012%

names or entities with the substring "lar"

occurrences of the word "Lar" and its variations

No Comments

No Known Activations