INDEX

Explanations

words related to exploration and investigation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

########.

-0.91

majánló

-0.85

 disambiguazione

-0.85

<pad>

-0.79

<unused52>

-0.79

<unused41>

-0.79

twimg

-0.79

<unused42>

-0.78

<unused74>

-0.78

<unused3>

-0.78

POSITIVE LOGITS

 explore

0.93

 exploring

0.91

 exploration

0.89

 Explore

0.84

 investigation

0.82

 explored

0.80

 investigate

0.80

 investigating

0.78

 investigations

0.77

explore

0.76

Activations Density 0.263%

words related to exploration and investigation

No Comments

No Known Activations