INDEX

Explanations

phrases related to unity or togetherness

oai_token-act-pair · gpt-3.5-turbo

terms related to group dynamics and communal experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

allery

-0.66

issance

-0.62

estate

-0.62

SHIP

-0.62

 Unloaded

-0.60

glomer

-0.60

owship

-0.59

 Mehran

-0.59

 with

-0.59

itchie

-0.58

POSITIVE LOGITS

 impunity

0.95

 regard

0.81

 hindsight

0.81

 abandon

0.80

 bang

0.76

 intention

0.75

 regards

0.73

 scissors

0.72

 ease

0.72

 linem

0.72

Activations Density 0.487%

phrases related to unity or togetherness

terms related to group dynamics and communal experiences

No Comments

No Known Activations