INDEX

Explanations

proper nouns or acronyms related to organizations or entities

oai_token-act-pair · gpt-3.5-turbo

acronyms, abbreviations, and references to organizations or entities

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

rities

-0.69

Unity

-0.64

atform

-0.64

steen

-0.63

 Visitors

-0.62

erity

-0.61

 Immortal

-0.60

 elusive

-0.59

 endowed

-0.58

 Admission

-0.57

POSITIVE LOGITS

pta

0.84

oslav

0.77

å£«

0.76

ilo

0.74

ificant

0.72

oku

0.70

agin

0.69

apist

0.69

atoon

0.69

omore

0.68

Activations Density 0.138%

proper nouns or acronyms related to organizations or entities

acronyms, abbreviations, and references to organizations or entities

No Comments

No Known Activations