INDEX

Explanations

hypothetical scenarios and conditional statements

oai_token-act-pair · gpt-3.5-turbo

conditional phrases starting with "if" that speculate about hypotheticals

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

 ());

-0.60

âĢĲ

-0.60

 ticks

-0.59

FIELD

-0.58

Accessory

-0.58

 Quarterly

-0.58

 Cutter

-0.57

Comments

-0.56

 Â¶

-0.56

ãģĦ

-0.56

POSITIVE LOGITS

isine

0.81

mble

0.78

eret

0.70

 feder

0.69

 somehow

0.68

 someday

0.67

prem

0.66

illet

0.66

inction

0.65

 hypot

0.64

Activations Density 0.159%

hypothetical scenarios and conditional statements

conditional phrases starting with "if" that speculate about hypotheticals

No Comments

No Known Activations