INDEX

Explanations

adjectives and descriptive phrases

oai_token-act-pair · gpt-3.5-turbo

phrases that express a combination of conditions or contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

".

-0.68

";

-0.63

"(

-0.62

chuk

-0.61

opian

-0.61

''.

-0.61

}.

-0.60

kill

-0.59

ombat

-0.57

.''

-0.56

POSITIVE LOGITS

 congr

0.64

 apologies

0.63

 irony

0.62

?)

0.59

0.58

 economists

0.56

 sarc

0.56

huh

0.55

 Bernstein

0.54

 automakers

0.54

Activations Density 2.095%

adjectives and descriptive phrases

phrases that express a combination of conditions or contexts

No Comments

No Known Activations