INDEX

Explanations

references to the city of Toronto

oai_token-act-pair · gpt-3.5-turbo

mentions of the city of Toronto

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

mble

-0.82

hardt

-0.81

bler

-0.77

vier

-0.74

ktop

-0.73

hard

-0.72

 Verb

-0.71

gins

-0.71

sole

-0.70

icio

-0.69

POSITIVE LOGITS

 Argon

0.94

 Raptors

0.93

 Toronto

0.87

 Harbour

0.84

 Centre

0.81

 Citiz

0.80

 Heights

0.79

 Maple

0.78

 Mississ

0.77

onto

0.75

Activations Density 0.013%

references to the city of Toronto

mentions of the city of Toronto

No Comments

No Known Activations