INDEX

Explanations

words related to a specific city or location

oai_token-act-pair · gpt-3.5-turbo

the word "Champagne" 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 @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Dolphin

-0.74

til

-0.67

 mole

-0.67

 underwater

-0.65

 spir

-0.64

 Jungle

-0.61

 undercut

-0.60

Ot

-0.59

 hypers

-0.59

 Knot

-0.58

POSITIVE LOGITS

aign

4.76

agne

3.21

agna

2.43

agn

1.25

inois

1.25

iard

1.04

gart

1.04

zig

1.04

ulhu

1.02

mingham

1.02

Activations Density 0.026%

words related to a specific city or location

the word "Champagne" and its variations

No Comments

No Known Activations