INDEX

Explanations

references to Elon Musk

oai_token-act-pair · gpt-3.5-turbo

mentions of Elon Musk

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

VI

-0.68

 Sussex

-0.67

 Veronica

-0.66

venge

-0.65

between

-0.65

×Ļ

-0.63

 sober

-0.62

 convent

-0.62

-0.61

 Columb

-0.60

POSITIVE LOGITS

 Musk

1.03

achev

0.87

daq

0.86

atu

0.85

estone

0.80

ONSORED

0.80

wagen

0.79

hattan

0.77

rats

0.77

borgh

0.77

Activations Density 0.009%

references to Elon Musk

mentions of Elon Musk

No Comments

No Known Activations