INDEX

Explanations

locations or places

oai_token-act-pair · gpt-3.5-turbo

names of geographic locations or regions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Owner

-0.63

 Selection

-0.60

 motto

-0.60

 philos

-0.59

agonist

-0.58

CHO

-0.57

ativity

-0.57

 spirited

-0.57

 isEnabled

-0.56

 outputs

-0.56

POSITIVE LOGITS

 Indies

0.89

 suburbs

0.83

 Springs

0.79

 Highlands

0.74

anish

0.74

 airspace

0.74

 Basin

0.71

iana

0.70

 meanwhile

0.68

isle

0.68

Activations Density 0.298%

locations or places

names of geographic locations or regions

No Comments

No Known Activations