INDEX

Explanations

words related to failure or unsuccessful outcomes

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "fail" 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

ourt

-0.73

iliary

-0.69

dar

-0.69

utra

-0.68

Austral

-0.65

arya

-0.64

Lug

-0.63

rete

-0.62

onen

-0.62

ript

-0.61

POSITIVE LOGITS

 miser

1.24

ingly

0.93

 catast

0.88

 horribly

0.86

lect

0.86

 dism

0.84

afe

0.81

fail

0.79

hard

0.78

DEV

0.72

Activations Density 0.019%

words related to failure or unsuccessful outcomes

occurrences of the word "fail" in various contexts

No Comments

No Known Activations