INDEX

Explanations

large numbers or quantifications

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "millions" and related numerical data within a context

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

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

wcsstore

-0.76

icter

-0.75

 Leilan

-0.75

 accompan

-0.70

ç«

-0.69

paio

-0.67

dress

-0.67

abus

-0.66

RH

-0.64

 neut

-0.62

POSITIVE LOGITS

hower

0.92

een

0.84

ortality

0.81

kees

0.78

riors

0.77

negie

0.75

 earners

0.74

riet

0.74

utenant

0.73

doms

0.73

Activations Density 0.120%

large numbers or quantifications

occurrences of the word "millions" and related numerical data within a context

No Comments

No Known Activations