INDEX

Explanations

verbs related to causing a change in state or property

oai_token-act-pair · gpt-3.5-turbo

words related to transformation or adaptation processes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tyard

-0.81

è¦ļéĨĴ

-0.71

swick

-0.71

stead

-0.70

VID

-0.69

raltar

-0.69

avering

-0.68

REL

-0.68

aterasu

-0.68

adra

-0.66

POSITIVE LOGITS

 oneself

0.80

 themselves

0.79

 notions

0.76

 itself

0.76

 tendencies

0.75

 existing

0.74

 into

0.72

 ourselves

0.68

 processes

0.67

enance

0.67

Activations Density 0.239%

verbs related to causing a change in state or property

words related to transformation or adaptation processes

No Comments

No Known Activations