INDEX

Explanations

reasons or explanations

oai_token-act-pair · gpt-3.5-turbo

expressions that indicate reasoning or justification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ty

-0.70

rop

-0.62

ãĥ¼ãĤ¯

-0.62

zman

-0.62

bow

-0.60

ãĤ¹

-0.60

 transm

-0.59

aith

-0.59

 exchanged

-0.58

prom

-0.58

POSITIVE LOGITS

 Canaver

0.89

why

0.87

soever

0.85

forth

0.79

ratulations

0.69

forward

0.68

 Emblem

0.65

terday

0.63

afa

0.62

we

0.61

Activations Density 0.041%

reasons or explanations

expressions that indicate reasoning or justification

No Comments

No Known Activations