INDEX

Explanations

words related to the term "im" that appear in various contexts

oai_token-act-pair · gpt-3.5-turbo

the word "im" and its variations, indicating a focus on identity or existence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

NetMessage

-1.00

chnology

-0.79

 grease

-0.70

 Sorceress

-0.66

 Parenthood

-0.66

 Chrys

-0.66

 dams

-0.66

cig

-0.64

Sv

-0.64

 brace

-0.63

POSITIVE LOGITS

ple

1.30

mediately

1.26

agine

1.24

perial

1.16

plementation

1.15

inished

1.14

ply

1.14

unity

1.12

pson

1.12

enez

1.12

Activations Density 0.028%

words related to the term "im" that appear in various contexts

the word "im" and its variations, indicating a focus on identity or existence

No Comments

No Known Activations