INDEX

Explanations

words related to isotopes

oai_token-act-pair · gpt-3.5-turbo

references to isotopes

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

 prisoner

-0.71

 tablet

-0.67

 crush

-0.66

 lith

-0.66

 kiss

-0.64

 servant

-0.60

 credit

-0.60

mar

-0.60

 barrier

-0.59

 Rookie

-0.59

POSITIVE LOGITS

opes

4.77

ope

2.13

oped

1.94

oping

1.87

OPE

1.86

opic

1.55

opers

1.36

opy

1.29

oops

1.14

omes

1.09

Activations Density 0.008%

words related to isotopes

references to isotopes

No Comments

No Known Activations