INDEX

Explanations

terms related to education, training, and decision-making

oai_token-act-pair · gpt-3.5-turbo

terminology and concepts related to evaluations, assessments, and structures 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 @ 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

apeake

-0.78

aples

-0.74

 Liberties

-0.72

 Dise

-0.72

VOL

-0.71

ufact

-0.71

ãĥĥãĥī

-0.69

å§«

-0.68

theless

-0.64

 mosqu

-0.64

POSITIVE LOGITS

ived

0.69

eker

0.67

undown

0.67

ipl

0.67

asers

0.65

placed

0.64

 outfit

0.63

els

0.63

imus

0.63

imal

0.62

Activations Density 0.575%

terms related to education, training, and decision-making

terminology and concepts related to evaluations, assessments, and structures in various contexts

No Comments

No Known Activations