INDEX

Explanations

instances of events or situations involving a specific entity or topic

oai_token-act-pair · gpt-3.5-turbo

references to specific cases or instances 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

reads

-0.74

ĵĺ

-0.74

ogie

-0.72

 fits

-0.69

 Madness

-0.67

bara

-0.66

orum

-0.66

 Mahjong

-0.65

orian

-0.63

 Practices

-0.63

POSITIVE LOGITS

 aforementioned

0.74

 ones

0.70

 remnants

0.66

 obligatory

0.64

pread

0.62

 mention

0.62

 infamous

0.60

ttes

0.60

ãĤ§

0.60

 pione

0.58

Activations Density 0.259%

instances of events or situations involving a specific entity or topic

references to specific cases or instances in various contexts

No Comments

No Known Activations