INDEX

Explanations

questions starting with "What is" or "What are"

oai_token-act-pair · gpt-3.5-turbo

the phrase "What is" 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

itches

-0.72

lems

-0.71

hyde

-0.69

heres

-0.68

tails

-0.66

hedon

-0.65

llah

-0.65

ience

-0.62

 lash

-0.62

gra

-0.60

POSITIVE LOGITS

omorphic

0.88

nt

0.78

 supposed

0.76

 happening

0.75

 actually

0.74

ãĤ»

0.73

 meant

0.72

?]

0.71

Ĥª

0.69

actually

0.68

Activations Density 0.084%

questions starting with "What is" or "What are"

the phrase "What is" in various contexts

No Comments

No Known Activations