INDEX

Explanations

instances of the word "hike" or "hiking"

oai_token-act-pair · gpt-3.5-turbo

references to various types of hikes or increases

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

Slot

-0.72

icator

-0.70

 Corpus

-0.70

binary

-0.69

liction

-0.69

Dialogue

-0.66

 healed

-0.64

istar

-0.63

 Saud

-0.62

ÑĮ

-0.61

POSITIVE LOGITS

 hike

0.90

 hiking

0.87

stakes

0.75

 hikes

0.75

iking

0.74

 biking

0.70

weed

0.69

jriwal

0.68

lift

0.67

otin

0.66

Activations Density 0.016%

instances of the word "hike" or "hiking"

references to various types of hikes or increases

No Comments

No Known Activations