INDEX

Explanations

names or references related to "Te" or "Teb" with different variations and contexts

oai_token-act-pair · gpt-3.5-turbo

specific character sequences or unique identifiers in the text

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

 tremend

-0.79

omaly

-0.70

 motives

-0.67

ģ«

-0.66

 boredom

-0.66

ĺħ

-0.64

¿½

-0.64

 privacy

-0.64

 specificity

-0.63

 anonymity

-0.63

POSITIVE LOGITS

inki

0.86

akeru

0.81

achus

0.71

initialized

0.71

asma

0.70

edd

0.69

ciating

0.69

abo

0.68

ettle

0.68

learning

0.67

Activations Density 0.082%

names or references related to "Te" or "Teb" with different variations and contexts

specific character sequences or unique identifiers in the text

No Comments

No Known Activations