INDEX

Explanations

names of individuals or groups, mainly referring to famous or notable figures

oai_token-act-pair · gpt-3.5-turbo

the word "the" in various contexts

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

iffe

-0.70

iest

-0.68

arer

-0.68

cture

-0.65

âĸł

-0.64

aeus

-0.64

NetMessage

-0.63

adesh

-0.63

peak

-0.62

AME

-0.62

POSITIVE LOGITS

 rest

1.53

 others

1.30

 accompanying

1.03

 Others

1.02

 other

1.01

 remainder

1.00

 adjoining

0.97

 consequ

0.97

 surrounding

0.96

 subsequent

0.91

Activations Density 0.148%

names of individuals or groups, mainly referring to famous or notable figures

the word "the" in various contexts

No Comments

No Known Activations