INDEX

Explanations

mentions of different social groups or communities

oai_token-act-pair · gpt-3.5-turbo

conjunctions and connectors that emphasize relationships among elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cules

-0.81

ģ«

-0.81

hani

-0.73

ONSORED

-0.66

inka

-0.64

 Achievements

-0.62

 reven

-0.62

Ïī

-0.61

zee

-0.61

ictive

-0.61

POSITIVE LOGITS

fil

0.70

Lew

0.62

speaking

0.60

igham

0.58

fters

0.58

Mand

0.58

ãĤī

0.58

uyomi

0.57

 Labrador

0.57

Ha

0.57

Activations Density 0.226%

mentions of different social groups or communities

conjunctions and connectors that emphasize relationships among elements

No Comments

No Known Activations