INDEX

Explanations

words related to objects or actions involving a pen

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "pen" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

enance

-0.67

ndum

-0.66

@@@@

-0.63

 Marxism

-0.62

 Normandy

-0.61

 Giuliani

-0.61

tt

-0.61

Duo

-0.58

 Bulg

-0.56

 Athe

-0.56

POSITIVE LOGITS

itent

1.70

ultimate

1.59

elope

1.43

cil

1.40

insula

1.40

alties

1.23

nington

1.18

manship

1.15

cill

1.07

ryn

1.01

Activations Density 0.032%

words related to objects or actions involving a pen

occurrences of the word "pen" and its variations

No Comments

No Known Activations