INDEX

Explanations

phrases that involve presenting options or outcomes

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a dichotomy or multiple categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ergy

-0.67

Beast

-0.66

Ire

-0.66

 Andromeda

-0.65

uddin

-0.61

olini

-0.60

une

-0.60

 rattled

-0.60

aukee

-0.60

DERR

-0.57

POSITIVE LOGITS

:-

1.10

%:

1.05

viz

1.02

0.92

 simultaneously

0.91

):

0.90

:(

0.88

':

0.87

:#

0.84

 depending

0.82

Activations Density 0.152%

phrases that involve presenting options or outcomes

phrases indicating a dichotomy or multiple categories

No Comments

No Known Activations