INDEX

Explanations

statements regarding plans, actions, and expectations in a context related to discussions or agreements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

tagHelperRunner

-0.74

writeFieldEnd

-0.66

 للمعارف

-0.66

URLException

-0.65

RUnlock

-0.64

')";

-0.64

Ngb

-0.63

 intStringLen

-0.61

>");

-0.59

PyExc

-0.59

POSITIVE LOGITS

 reportedly

0.80

 apparently

0.71

 probably

0.67

apparently

0.60

probably

0.60

 supposedly

0.57

presumably

0.55

 presumably

0.54

 evidently

0.52

 according

0.51

Activations Density 0.701%

statements regarding plans, actions, and expectations in a context related to discussions or agreements

No Comments

No Known Activations