INDEX

Explanations

instances where instructions or actions are being suggested or described

oai_token-act-pair · gpt-3.5-turbo

verbs related to actions that involve engagement or participation

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

heim

-0.73

nton

-0.70

EMS

-0.66

lat

-0.64

 unveiling

-0.60

dt

-0.59

cerning

-0.59

ether

-0.58

can

-0.57

hester

-0.57

POSITIVE LOGITS

ependent

0.74

irection

0.71

oaded

0.67

 starve

0.67

 something

0.66

ivated

0.66

redients

0.66

utical

0.64

 hypocr

0.64

ivable

0.64

Activations Density 0.257%

instances where instructions or actions are being suggested or described

verbs related to actions that involve engagement or participation

No Comments

No Known Activations