INDEX

Explanations

names of individuals with varying levels of activation

oai_token-act-pair · gpt-3.5-turbo

names of key individuals mentioned in the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ModLoader

-0.72

âĶĢâĶĢ

-0.61

theless

-0.57

 Fancy

-0.54

acebook

-0.53

ãĥŁ

-0.53

 Madame

-0.52

âĸ¬

-0.51

sburgh

-0.50

 Oprah

-0.50

POSITIVE LOGITS

erman

0.70

gaard

0.70

zinski

0.70

beck

0.67

linger

0.67

zen

0.66

zynski

0.66

lett

0.65

stad

0.65

burn

0.64

Activations Density 0.247%

names of individuals with varying levels of activation

names of key individuals mentioned in the document

No Comments

No Known Activations