INDEX

Explanations

phrases related to stopping or halting actions

oai_token-act-pair · gpt-3.5-turbo

references to stopping or halting actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

STEM

-0.69

urable

-0.68

bender

-0.68

hood

-0.64

 resilient

-0.62

nostic

-0.62

 landslide

-0.61

elf

-0.61

matter

-0.60

xml

-0.59

POSITIVE LOGITS

 Brunswick

0.70

Lago

0.69

anwhile

0.67

 Restaur

0.66

 restaurants

0.66

 Bangkok

0.66

 locations

0.65

 Takeru

0.65

opol

0.65

 Chero

0.64

Activations Density 0.130%

phrases related to stopping or halting actions

references to stopping or halting actions

No Comments

No Known Activations