INDEX

Explanations

political or authoritative terms, often relating to power or control

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "reign" and its variations

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

ertodd

-0.79

Quotes

-0.69

hammad

-0.68

FFER

-0.66

 Friendly

-0.62

 Humanity

-0.61

----------------

-0.60

 contrace

-0.59

 Spiel

-0.58

WER

-0.57

POSITIVE LOGITS

pin

0.85

ited

0.84

ieved

0.78

unders

0.77

uin

0.75

der

0.74

esses

0.74

oct

0.73

iever

0.71

Activations Density 0.011%

political or authoritative terms, often relating to power or control

occurrences of the word "reign" and its variations

No Comments

No Known Activations