INDEX

Explanations

actions related to locking or being locked in a physical or metaphorical sense

oai_token-act-pair · gpt-3.5-turbo

instances of the word "lock" 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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

FUL

-0.67

ITNESS

-0.64

 luck

-0.62

 referrals

-0.58

 suggestions

-0.58

 persuasion

-0.57

 rainbow

-0.56

Pam

-0.55

 Examples

-0.55

 Scholarship

-0.55

POSITIVE LOGITS

 tightly

1.13

 securely

1.09

 shut

1.01

 indefinitely

0.97

lock

0.95

 doors

0.95

recy

0.93

 tight

0.93

 behind

0.90

tight

0.89

Activations Density 0.165%

actions related to locking or being locked in a physical or metaphorical sense

instances of the word "lock" and its variations

No Comments

No Known Activations