INDEX

Explanations

Keywords related to specific individuals, organizations, and locations

oai_token-act-pair · gpt-3.5-turbo

explicit references to significant events or actions

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

 âĺħ

-0.54

\",

-0.52

 irreversible

-0.51

COMPLE

-0.51

 Depression

-0.50

âĺħâĺħ

-0.50

LOS

-0.50

advertisement

-0.48

 depression

-0.48

âĺħ

-0.48

POSITIVE LOGITS

anwhile

0.88

 latter

0.68

yip

0.63

 respectively

0.60

undai

0.58

 incorpor

0.58

 Leilan

0.57

 Together

0.55

 mileage

0.54

Ago

0.54

Activations Density 0.992%

Keywords related to specific individuals, organizations, and locations

explicit references to significant events or actions

No Comments

No Known Activations