INDEX

Explanations

It appears that neuron 4 does not activate for any of the provided tokens, which suggests it might be looking for something not present in the provided text excerpts or that it might be malfunctioning or inactive

oai_token-act-pair · gpt-4-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

latest

-0.72

ache

-0.72

awa

-0.68

dylib

-0.67

notations

-0.67

++)

-0.66

 residues

-0.64

google

-0.64

soever

-0.63

Ĥİ

-0.63

POSITIVE LOGITS

 Watt

0.73

rouse

0.71

nect

0.68

uras

0.68

ner

0.67

Buk

0.62

aan

0.62

ners

0.62

slave

0.60

rament

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.