INDEX

Explanations

names and entities related to sports and entertainment figures

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

torch.float32

Hook Point

blocks.12.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

HuggingFaceFW/fineweb

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.73

-0.97

<eos>

-0.93

and

-0.92

-0.90

for

-0.90

in

-0.90

at

-0.88

on

-0.88

if

-0.88

POSITIVE LOGITS

 lele

2.35

 alkoh

2.33

 dises

2.32

 kram

2.31

mef

2.29

 cannes

2.28

 wien

2.28

 embra

2.22

 stockholm

2.22

 milano

2.22

Activations Density 0.768%

names and entities related to sports and entertainment figures

No Comments

No Known Activations