INDEX

Explanations

instances where actions or procedures are being carried out or recommended

oai_token-act-pair · gpt-3.5-turbo

instances of the word "apply" and its variations in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

acters

-0.71

owship

-0.70

hoff

-0.68

footed

-0.67

airs

-0.63

OUS

-0.61

 Island

-0.61

birds

-0.61

beck

-0.61

keeping

-0.60

POSITIVE LOGITS

 pressure

0.92

arate

0.71

 sunscreen

0.69

rals

0.66

aution

0.62

 Anarchy

0.62

 liber

0.61

enz

0.61

 rigorous

0.60

 muster

0.60

Activations Density 0.034%

instances where actions or procedures are being carried out or recommended

instances of the word "apply" and its variations in various contexts

No Comments

No Known Activations