INDEX

Explanations

phrases related to societal structures and beliefs

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "world" 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

veyard

-0.86

 actionGroup

-0.84

oug

-0.78

ippi

-0.78

aturday

-0.75

etsk

-0.74

ibility

-0.74

utenant

-0.71

IFF

-0.71

odox

-0.70

POSITIVE LOGITS

liness

0.92

building

0.82

scape

0.74

eers

0.73

 revolves

0.73

icz

0.69

arium

0.68

fare

0.67

 outlook

0.66

 economy

0.65

Activations Density 0.054%

phrases related to societal structures and beliefs

references to the concept of "world" in various contexts

No Comments

No Known Activations