INDEX

Explanations

occurrences of the word "Per" and variations indicating a relation to "perception" or "permission"

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

}}/>

-0.86

$}}

-0.76

"]

-0.75

********/

-0.74

$.

-0.74

$")

-0.74

$]$

-0.73

 Theſe

-0.73

POSITIVE LOGITS

Per

3.51

per

3.48

Per

3.37

per

3.05

PER

2.96

PER

2.84

 Perkins

1.59

 peric

1.58

 Perch

1.53

perg

1.49

Activations Density 0.069%

occurrences of the word "Per" and variations indicating a relation to "perception" or "permission"

No Comments

No Known Activations