INDEX

Explanations

phrases indicating sequence or ordering

oai_token-act-pair · gpt-3.5-turbo

instances of the word "followed" 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 @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

pite

-0.74

vere

-0.71

negie

-0.68

bent

-0.67

cit

-0.64

idad

-0.63

anyon

-0.63

orc

-0.62

uras

-0.62

rimination

-0.61

POSITIVE LOGITS

ĸļ

0.91

Īè

0.86

 follows

0.85

 closely

0.81

 followed

0.81

 follow

0.72

 suit

0.72

¿½

0.71

follow

0.70

 faithfully

0.69

Activations Density 0.025%

phrases indicating sequence or ordering

instances of the word "followed" and its variations

No Comments

No Known Activations