INDEX

Explanations

statements where an individual or organization is expressing a position or action

oai_token-act-pair · gpt-3.5-turbo

the verb "was" 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

ossom

-0.73

aign

-0.69

 Recession

-0.68

 flourish

-0.67

vertisement

-0.67

 ends

-0.65

izes

-0.63

 looms

-0.61

 confines

-0.60

alus

-0.60

POSITIVE LOGITS

nt

0.90

 owed

0.87

 indeed

0.85

not

0.82

 definitely

0.81

absolutely

0.79

 unlikely

0.79

rael

0.75

not

0.73

 unequiv

0.72

Activations Density 0.309%

statements where an individual or organization is expressing a position or action

the verb "was" in various contexts

No Comments

No Known Activations