INDEX

Explanations

phrases related to triggering events or actions

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate triggering or initiating events

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

umbing

-0.75

basketball

-0.65

uddy

-0.62

 Weld

-0.61

%]

-0.60

ockey

-0.59

Obj

-0.58

hai

-0.57

 entirety

-0.57

mol

-0.57

POSITIVE LOGITS

cffffcc

0.87

nings

0.74

 alarm

0.73

bolt

0.66

 alarms

0.64

ragon

0.63

 pist

0.63

 havoc

0.63

DEF

0.62

anger

0.62

Activations Density 0.022%

phrases related to triggering events or actions

phrases that indicate triggering or initiating events

No Comments

No Known Activations