INDEX

Explanations

names related to various locations and individuals

oai_token-act-pair · gpt-3.5-turbo

names and shout-outs related to people or entities

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

cig

-0.71

«ĺ

-0.69

¬¼

-0.68

 Labrador

-0.68

 dummy

-0.67

 occas

-0.64

 Viking

-0.64

 Fenrir

-0.63

ablishment

-0.62

 restraints

-0.61

POSITIVE LOGITS

 Shak

1.04

lar

0.93

arak

0.90

aji

0.90

ti

0.88

ilo

0.86

spe

0.86

uras

0.85

htar

0.85

tered

0.85

Activations Density 0.011%

names related to various locations and individuals

names and shout-outs related to people or entities

No Comments

No Known Activations