INDEX

Explanations

mentions of the word "Whit" and variations of the word appearing in the text

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Whit"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

PsyNetMessage

-0.97

igslist

-0.77

 GEAR

-0.76

 mileage

-0.71

UTE

-0.67

repre

-0.66

 prec

-0.66

REF

-0.65

 gravity

-0.65

Reference

-0.64

POSITIVE LOGITS

ewater

1.46

eness

1.25

bread

1.25

eless

1.08

comb

1.07

elist

1.06

acre

1.06

ened

1.05

ney

1.05

ening

1.04

Activations Density 0.034%

mentions of the word "Whit" and variations of the word appearing in the text

mentions of the name "Whit"

No Comments

No Known Activations