INDEX

Explanations

words related to speculation and uncertain claims

oai_token-act-pair · gpt-3.5-turbo

instances of the word "spec" and its variants, suggesting a focus on speculation and conjecture

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

etheless

-0.80

jiang

-0.71

warm

-0.69

 Holding

-0.67

¿½

-0.64

 standby

-0.64

 destro

-0.62

 Hearts

-0.60

 Cruel

-0.60

 disarm

-0.59

POSITIVE LOGITS

ulations

1.12

ifications

1.11

ifiers

1.04

imen

1.04

imens

1.03

ulators

0.96

ript

0.96

ifiable

0.94

iper

0.92

ete

0.91

Activations Density 0.019%

words related to speculation and uncertain claims

instances of the word "spec" and its variants, suggesting a focus on speculation and conjecture

No Comments

No Known Activations