INDEX

Explanations

proper nouns containing the substring 'aw'

oai_token-act-pair · gpt-3.5-turbo

the presence of the word "Taw," indicating a focus on a specific name or term

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

 Luthor

-0.72

 Luther

-0.72

 Scotia

-0.68

 Juda

-0.68

 Mayhem

-0.67

 Panzer

-0.66

 ejac

-0.66

 Hitler

-0.66

 McMaster

-0.65

 steroids

-0.63

POSITIVE LOGITS

esome

1.41

akening

1.35

aii

1.24

aw

1.10

akens

1.10

yer

1.09

dry

1.07

atche

1.06

ashington

1.03

orks

1.02

Activations Density 0.016%

proper nouns containing the substring 'aw'

the presence of the word "Taw," indicating a focus on a specific name or term

No Comments

No Known Activations