INDEX

Explanations

interview-related content and conversational tones

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

TypedDataSet

-0.61

baldi

-0.59

idalgo

-0.54

 molecular

-0.53

ību

-0.52

digd

-0.52

hyo

-0.51

();?>

-0.51

ῖς

-0.51

MULTIPLE

-0.49

POSITIVE LOGITS

 conversational

0.96

 conversation

0.95

 interview

0.91

 interviewer

0.90

 chatting

0.88

conversation

0.80

 autobio

0.80

 conversations

0.78

 chat

0.78

 Interview

0.76

Activations Density 0.305%

interview-related content and conversational tones

No Comments

No Known Activations