INDEX

Explanations

names of places or people

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names and locations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rez

-0.61

ãĥ£

-0.61

orsche

-0.56

Si

-0.55

Qi

-0.54

hered

-0.51

dozen

-0.51

 Quake

-0.51

aughtered

-0.51

ibilities

-0.51

POSITIVE LOGITS

's

0.84

+.

0.79

 herself

0.78

 himself

0.77

 Productions

0.76

 itself

0.75

ruary

0.71

Tube

0.71

AFB

0.69

tsy

0.69

Activations Density 0.361%

names of places or people

proper nouns, specifically names and locations

No Comments

No Known Activations