INDEX

Explanations

terms related to compounding factors or elements

oai_token-act-pair · gpt-3.5-turbo

terms related to compounding effects and geographical locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

bors

-0.95

ľ

-0.90

Ļ½

-0.88

 tracts

-0.88

pta

-0.84

ylum

-0.84

hov

-0.81

peace

-0.81

llah

-0.78

Ľ

-0.76

POSITIVE LOGITS

 Lanc

0.83

 Seym

0.77

edged

0.73

 compounded

0.71

icular

0.70

 clipboard

0.70

akening

0.65

 borrowing

0.65

icates

0.65

edge

0.64

Activations Density 0.030%

terms related to compounding factors or elements

terms related to compounding effects and geographical locations

No Comments

No Known Activations