INDEX

Explanations

prepositions used to indicate the relationship between two elements

oai_token-act-pair · gpt-3.5-turbo

phrases indicating time frames or contexts related to actions or events

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

umbn

-0.73

 needed

-0.67

itiz

-0.64

assic

-0.63

rouse

-0.60

 messenger

-0.60

 Booker

-0.59

amen

-0.59

 desired

-0.58

igers

-0.58

POSITIVE LOGITS

itialized

0.85

neath

0.82

ward

0.79

 Racer

0.77

%:

0.75

ventory

0.75

 Features

0.74

asionally

0.73

ctr

0.72

math

0.72

Activations Density 0.106%

prepositions used to indicate the relationship between two elements

phrases indicating time frames or contexts related to actions or events

No Comments

No Known Activations