INDEX

Explanations

names of programming elements marked with 'object'

oai_token-act-pair · gpt-3.5-turbo

references to objects in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 millenn

-1.02

mph

-0.86

hiba

-0.78

DAY

-0.77

icago

-0.76

cling

-0.74

HAEL

-0.74

aturdays

-0.74

ornia

-0.73

creen

-0.73

POSITIVE LOGITS

 Object

0.93

 objects

0.91

object

0.88

objects

0.85

 object

0.84

obj

0.83

 Objects

0.82

Obj

0.78

 Token

0.77

ifier

0.77

Activations Density 0.009%

names of programming elements marked with 'object'

references to objects in programming contexts

No Comments

No Known Activations