INDEX

Explanations

references to water-related locations, possibly related to a legal or administrative context

oai_token-act-pair · gpt-3.5-turbo

references to water-related entities or concepts

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

senal

-0.76

Reloaded

-0.76

cius

-0.69

ogenic

-0.69

============

-0.68

ures

-0.67

 blinded

-0.66

cial

-0.63

 mort

-0.62

*/(

-0.62

POSITIVE LOGITS

restling

1.07

Nap

0.94

Aid

0.85

robe

0.85

isconsin

0.85

dropping

0.83

ingham

0.83

esley

0.80

ITNESS

0.78

orthy

0.78

Activations Density 0.017%

references to water-related locations, possibly related to a legal or administrative context

references to water-related entities or concepts

No Comments

No Known Activations