INDEX

Explanations

phrases indicating a key point or essential factor

oai_token-act-pair · gpt-3.5-turbo

phrases that include the word "to," often indicating a conclusion or outcome

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

igham

-0.75

icion

-0.71

interstitial

-0.70

iott

-0.69

notations

-0.68

handled

-0.67

icipated

-0.67

went

-0.65

ventures

-0.65

oyer

-0.65

POSITIVE LOGITS

othy

0.77

 earth

0.71

 ashes

0.63

 thirds

0.63

 basics

0.61

 pasture

0.61

 gravity

0.60

 sheer

0.59

 scoreboard

0.58

TPS

0.58

Activations Density 0.038%

phrases indicating a key point or essential factor

phrases that include the word "to," often indicating a conclusion or outcome

No Comments

No Known Activations