INDEX

Explanations

mentions or references to the Stanley Cup

oai_token-act-pair · gpt-3.5-turbo

references to the Stanley Cup

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

ged

-0.93

gil

-0.82

hy

-0.81

anwhile

-0.79

ansas

-0.78

nir

-0.78

gel

-0.77

du

-0.76

lez

-0.76

htar

-0.75

POSITIVE LOGITS

 Kubrick

1.07

 Stanley

0.90

 Winter

0.80

 Baldwin

0.80

thal

0.80

 Transactions

0.78

 Bros

0.70

 Clarke

0.70

 Robinson

0.70

 Games

0.69

Activations Density 0.014%

mentions or references to the Stanley Cup

references to the Stanley Cup

No Comments

No Known Activations