INDEX

Explanations

descriptions or narratives related to mundane activities or situations

oai_token-act-pair · gpt-3.5-turbo

elements and descriptors related to physical surroundings and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ITNESS

-0.64

operation

-0.61

Recommend

-0.61

Statement

-0.59

 confir

-0.59

<[

-0.58

endment

-0.57

ERG

-0.57

 Protective

-0.57

emort

-0.56

POSITIVE LOGITS

 throb

0.77

 hilar

0.75

 garg

0.75

 throats

0.75

 whim

0.71

 spew

0.71

 hordes

0.70

 drunken

0.70

gul

0.67

livion

0.66

Activations Density 2.124%

descriptions or narratives related to mundane activities or situations

elements and descriptors related to physical surroundings and experiences

No Comments

No Known Activations