INDEX

Explanations

the question "What is" followed by a specific topic or concept

oai_token-act-pair · gpt-3.5-turbo

questions or phrases that start with "What is."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Chev

-0.67

 Towers

-0.66

 Hitch

-0.63

 Peoples

-0.61

ikers

-0.61

udeau

-0.60

 Isles

-0.60

 Lann

-0.59

heres

-0.59

itches

-0.58

POSITIVE LOGITS

 supposed

0.84

nt

0.82

actually

0.81

omorphic

0.77

 presently

0.76

really

0.75

 actually

0.75

 ultimately

0.75

 happening

0.75

 transpired

0.74

Activations Density 0.153%

the question "What is" followed by a specific topic or concept

questions or phrases that start with "What is."

No Comments

No Known Activations