INDEX

Explanations

phrases related to causes or motivations

oai_token-act-pair · gpt-3.5-turbo

rhetorical questions and statements that introduce a topic

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

arat

-0.77

enburg

-0.64

anchester

-0.63

wal

-0.63

ws

-0.62

oeuv

-0.62

holiday

-0.61

yon

-0.59

kel

-0.59

ndum

-0.59

POSITIVE LOGITS

 namely

0.77

TEXTURE

0.61

 inclusion

0.60

 Qualcomm

0.60

 consistency

0.58

 Parm

0.58

 longevity

0.57

ãĢĳ

0.56

DOS

0.56

 graphene

0.55

Activations Density 0.393%

phrases related to causes or motivations

rhetorical questions and statements that introduce a topic

No Comments

No Known Activations