INDEX

Explanations

terms related to remnants or remains

oai_token-act-pair · gpt-3.5-turbo

references to remains in various contexts, particularly related to physical objects or entities that are no longer intact

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

æ©Ł

-0.83

é¾

-0.74

NRS

-0.73

 externalToEVAOnly

-0.73

ussen

-0.69

æĪ¦

-0.68

 ratings

-0.65

yrinth

-0.65

 Rating

-0.64

âĺħâĺħ

-0.63

POSITIVE LOGITS

 thereof

0.84

atile

0.78

 lodged

0.73

 Missing

0.73

pel

0.73

waters

0.72

 remnants

0.72

 remains

0.71

cano

0.71

pora

0.71

Activations Density 0.030%

terms related to remnants or remains

references to remains in various contexts, particularly related to physical objects or entities that are no longer intact

No Comments

No Known Activations