INDEX

Explanations

statements related to hypotheses and evidence concerning claims, particularly in a political or investigative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 MyApp

-0.60

 Wicidata

-0.58

собенности

-0.56



-0.55

réhen

-0.55

serviceWorker

-0.55

fhir

-0.53

 inflater

-0.52

béco

-0.51

POSITIVE LOGITS

 confirmation

1.29

 confirmed

1.17

 confirm

1.16

 verification

1.14

 Confirmed

1.10

 verified

1.08

 verify

1.08

 verifying

1.07

 confirms

1.07

 confirming

1.07

Activations Density 0.614%

statements related to hypotheses and evidence concerning claims, particularly in a political or investigative context

No Comments

No Known Activations