INDEX

Explanations

terms related to teenagers

oai_token-act-pair · gpt-3.5-turbo

references to teenagers

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

leased

-0.78

ļé

-0.76

ł

-0.76

veyard

-0.72

¢

-0.72

staff

-0.70

rote

-0.69

ãģĤ

-0.69

SHIP

-0.69

ľ

-0.68

POSITIVE LOGITS

cape

0.82

 aged

0.81

uates

0.74

ishly

0.73

who

0.73

 Anonymous

0.70

 Trayvon

0.70

ish

0.69

0.68

hips

0.67

Activations Density 0.027%

terms related to teenagers

references to teenagers

No Comments

No Known Activations