INDEX

Explanations

phrases indicating uncertainty or choice

oai_token-act-pair · gpt-3.5-turbo

repeated usage of the word "which" across various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Rog

-0.81

GROUND

-0.79

Balt

-0.76

kj

-0.73

bly

-0.72

kamp

-0.71

UX

-0.71

FINE

-0.69

 Glob

-0.69

fitting

-0.67

POSITIVE LOGITS

 kinds

0.91

 sorts

0.81

soever

0.78

 redes

0.76

 types

0.74

 direction

0.70

 kind

0.70

 flavors

0.69

 contingency

0.68

 ones

0.66

Activations Density 0.051%

phrases indicating uncertainty or choice

repeated usage of the word "which" across various contexts

No Comments

No Known Activations