INDEX

Explanations

phrases related to reasoning or justification

oai_token-act-pair · gpt-3.5-turbo

the word "because," indicating causal relationships in statements

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

agin

-0.78

yan

-0.75

nin

-0.74

mint

-0.72

wn

-0.72

Gas

-0.69

lem

-0.67

Luc

-0.67

thal

-0.64

ries

-0.64

POSITIVE LOGITS

*/(

0.90

uristic

0.75

 proxies

0.74

endment

0.72

 they

0.71

ority

0.69

ecause

0.67

akening

0.67

urers

0.65

uras

0.64

Activations Density 0.079%

phrases related to reasoning or justification

the word "because," indicating causal relationships in statements

No Comments

No Known Activations