INDEX

Explanations

words related to geography or locations, possibly focusing on specific place names

oai_token-act-pair · gpt-3.5-turbo

words that contain specific consonant structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 latent

-0.71

 unexpl

-0.70

Magikarp

-0.69

 admiration

-0.67

 discrimination

-0.66

 discriminate

-0.65

 goodwill

-0.65

 invention

-0.62

 depressive

-0.61

 infringing

-0.61

POSITIVE LOGITS

veland

0.83

onica

0.80

heed

0.79

*/(

0.74

hemy

0.73

nces

0.73

voy

0.71

ico

0.70

berus

0.70

vette

0.69

Activations Density 0.090%

words related to geography or locations, possibly focusing on specific place names

words that contain specific consonant structures

No Comments

No Known Activations