INDEX

Explanations

words related to the concept of being resistant to damage or harm

oai_token-act-pair · gpt-3.5-turbo

instances of the word "proof" 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

Negative Logits

ets

-0.68

cho

-0.65

 affiliates

-0.64

 quer

-0.63

 Sector

-0.63

ms

-0.62

ETS

-0.61

 Middle

-0.60

 beet

-0.60

 Mare

-0.59

POSITIVE LOGITS

proof

4.56

Proof

2.63

 proof

2.20

 Proof

2.16

resistant

1.69

 proofs

1.53

evidence

1.33

safe

1.15

tight

1.01

proven

0.97

Activations Density 0.014%

words related to the concept of being resistant to damage or harm

instances of the word "proof" and its variations

No Known Activations