INDEX

Explanations

instances where the action of looking or searching for something is mentioned

oai_token-act-pair · gpt-3.5-turbo

instances of the word "look" 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 @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

âĹ¼

-0.68

theless

-0.66

Failure

-0.65

RIC

-0.63

Els

-0.63

accompan

-0.61

kson

-0.61

rots

-0.59

CENT

-0.57

versive

-0.57

POSITIVE LOGITS

 closely

0.97

behind

0.85

 around

0.84

 inside

0.84

 elsewhere

0.83

 carefully

0.82

ahead

0.79

up

0.79

 deeper

0.78

 into

0.78

Activations Density 0.052%

instances where the action of looking or searching for something is mentioned

instances of the word "look" and its variations

No Comments

No Known Activations