INDEX

Explanations

references to TV shows

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PYX

-0.64

 elde

-0.57

expandindo

-0.56

ContentAlignment

-0.56

RenderAtEndOf

-0.56

 liggen

-0.54

 paard

-0.52

ardige

-0.51

 daarvoor

-0.51

]').

-0.50

POSITIVE LOGITS

 show

4.47

 Show

3.97

show

3.91

Show

3.73

 SHOW

3.66

SHOW

3.31

 shows

2.71

 Shows

2.54

 shew

2.52

shows

2.47

Activations Density 0.148%

references to TV shows

No Comments

No Known Activations