INDEX

Explanations

phrases indicating simultaneity or concurrent actions

oai_token-act-pair · gpt-3.5-turbo

references to the concept of time

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

 fingert

-0.66

 stun

-0.66

 unequ

-0.62

Kau

-0.61

 basement

-0.60

elin

-0.60

avorite

-0.60

Fit

-0.60

LCS

-0.59

 boun

-0.59

POSITIVE LOGITS

å¥³

0.94

frames

0.79

âĶĢâĶĢ

0.79

BUS

0.78

yang

0.77

HCR

0.76

days

0.72

essage

0.71

²¾

0.69

cross

0.69

Activations Density 0.017%

phrases indicating simultaneity or concurrent actions

references to the concept of time

No Comments

No Known Activations