INDEX

Explanations

words that signify a positive assessment or value judgment

oai_token-act-pair · gpt-3.5-turbo

phrases and contexts indicating well-being or favorable conditions

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

anos

-0.72

pid

-0.68

avorite

-0.65

 Duck

-0.64

mare

-0.64

ierce

-0.63

rush

-0.62

rys

-0.62

anus

-0.61

 Samp

-0.60

POSITIVE LOGITS

itia

0.62

 vers

0.60

 evidenced

0.60

________________________________________________________________

0.59

ãĥ´

0.59

onse

0.59

SPONSORED

0.58

 optionally

0.58

ORT

0.58

 insofar

0.57

Activations Density 0.030%

words that signify a positive assessment or value judgment

phrases and contexts indicating well-being or favorable conditions

No Comments

No Known Activations