INDEX

Explanations

words related to financial transactions or deals

oai_token-act-pair · gpt-3.5-turbo

elements associated with negative or derogatory descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

hedral

-0.70

oslav

-0.67

ĸļ

-0.65

MSN

-0.65

wake

-0.62

hu

-0.62

RAL

-0.62

iq

-0.61

ujah

-0.61

Ply

-0.61

POSITIVE LOGITS

itely

0.67

eele

0.63

ħĭ

0.62

bender

0.61

iaries

0.59

BILITIES

0.59

 Portug

0.57

ãĥīãĥ©

0.57

tein

0.57

upper

0.56

Activations Density 0.163%

words related to financial transactions or deals

elements associated with negative or derogatory descriptions

No Comments

No Known Activations