INDEX

Explanations

words related to fostering and care, particularly in the context of children or communities

oai_token-act-pair · gpt-3.5-turbo

terms related to fostering and care, particularly in social settings

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

uyomi

-0.78

adesh

-0.74

NetMessage

-0.68

ngth

-0.67

anwhile

-0.67

ipop

-0.67

ivan

-0.67

tery

-0.66

uters

-0.65

 Antar

-0.65

POSITIVE LOGITS

 foster

0.84

wcsstore

0.71

 fost

0.71

 fostering

0.69

resses

0.68

ress

0.68

 nurturing

0.65

tails

0.65

 ment

0.63

rament

0.63

Activations Density 0.013%

words related to fostering and care, particularly in the context of children or communities

terms related to fostering and care, particularly in social settings

No Comments

No Known Activations