INDEX

Explanations

references to a specific name or term, possibly related to an author or character in a narrative

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

 voork

-0.57

 mxArray

-0.56

wz

-0.55

 snippetHide

-0.53

glades

-0.52

siębior

-0.52

coltà

-0.52

getJSONArray

-0.51

holtz

-0.51

FORE

-0.50

POSITIVE LOGITS

ze

3.46

ZE

2.54

Ze

2.11

Ze

1.84

ze

1.78

ZE

1.45

zes

1.41

zed

1.34

zeg

1.25

zeh

1.19

Activations Density 0.067%

references to a specific name or term, possibly related to an author or character in a narrative

No Comments

No Known Activations