INDEX

Explanations

instances where two entities have something in common

oai_token-act-pair · gpt-3.5-turbo

words related to sharing, including their variations in context

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

paio

-0.68

ibur

-0.67

veyard

-0.66

anwhile

-0.66

 reper

-0.66

iffe

-0.65

 desper

-0.64

pmwiki

-0.62

esa

-0.60

mental

-0.60

POSITIVE LOGITS

cro

0.89

 similarities

0.78

hare

0.78

mates

0.77

holders

0.72

Redd

0.72

holding

0.67

 pointers

0.67

emonium

0.67

rists

0.67

Activations Density 0.026%

instances where two entities have something in common

words related to sharing, including their variations in context

No Comments

No Known Activations