INDEX

Explanations

proper nouns in various languages related to locations

oai_token-act-pair · gpt-3.5-turbo

words related to healthcare and medical conditions

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

Analysis

-0.68

Fair

-0.67

ELF

-0.64

Making

-0.64

Inc

-0.63

 Accountability

-0.61

Shock

-0.61

Full

-0.60

Notice

-0.60

Trigger

-0.59

POSITIVE LOGITS

 pione

0.84

pta

0.84

kan

0.80

mi

0.77

jet

0.75

iage

0.74

inem

0.74

 gust

0.73

vi

0.73

tro

0.73

Activations Density 0.125%

proper nouns in various languages related to locations

words related to healthcare and medical conditions

No Comments

No Known Activations