INDEX

Explanations

adjectives or verbs associated with judgment or evaluation

oai_token-act-pair · gpt-3.5-turbo

terms related to evaluation and critique of media or projects

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

bara

-0.60

bill

-0.59

ingham

-0.57

eligible

-0.56

ajo

-0.56

ende

-0.54

avers

-0.53

¿½

-0.53

apo

-0.53

isman

-0.52

POSITIVE LOGITS

 somew

0.68

 carbs

0.65

 spoilers

0.61

 disclaimer

0.60

 chronological

0.58

 masturbation

0.58

 multiplayer

0.58

wee

0.56

 christ

0.56

 monog

0.55

Activations Density 1.113%

adjectives or verbs associated with judgment or evaluation

terms related to evaluation and critique of media or projects

No Comments

No Known Activations