INDEX

Explanations

statements or actions related to decision-making and information-sharing

oai_token-act-pair · gpt-3.5-turbo

phrases related to collective experiences and community dynamics

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

Downloadha

-0.64

soever

-0.60

 herself

-0.58

 clipboard

-0.57

 Digest

-0.56

EVA

-0.56

 Ambro

-0.54

 guiActiveUn

-0.53

ikuman

-0.53

CRC

-0.52

POSITIVE LOGITS

 ourselves

1.54

our

0.93

 ours

0.82

OUR

0.76

 asses

0.67

 selves

0.67

 together

0.60

Our

0.59

yg

0.59

 collectively

0.58

Activations Density 0.839%

statements or actions related to decision-making and information-sharing

phrases related to collective experiences and community dynamics

No Comments

No Known Activations