INDEX

Explanations

negations or denials related to different subjects or claims

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 pavillon

-0.55

 consultato

-0.50

getattr

-0.47

HttpPost

-0.47

 taget

-0.47

uoti

-0.46

ям

-0.46

StringTo

-0.45

bitset

-0.45

itas

-0.45

POSITIVE LOGITS

MigrationBuilder

0.79

 CURLOPT

0.66

saraba

0.62

 дописавши

0.61

PyExc

0.59

RegressionTest

0.58

 autorytatywna

0.56



0.55

'},

0.54

anoma

0.54

Activations Density 0.077%

negations or denials related to different subjects or claims

No Comments

No Known Activations