INDEX

Explanations

verbs indicating a change or transition

oai_token-act-pair · gpt-3.5-turbo

instances of past actions or changes over time

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

Ney

-0.66

ocal

-0.63

 ideal

-0.62

 Defenders

-0.58

 backbone

-0.57

iour

-0.56

 constituents

-0.56

 withstand

-0.56

ribes

-0.55

ested

-0.54

POSITIVE LOGITS

isode

0.77

Ń·

0.77

Cooldown

0.76

Bye

0.71

 adjourn

0.70

cember

0.69

 abruptly

0.67

END

0.67

 trave

0.66

ĻĤ

0.66

Activations Density 0.301%

verbs indicating a change or transition

instances of past actions or changes over time

No Comments

No Known Activations