INDEX

Explanations

text structuring and formatting cues

oai_token-act-pair · gpt-3.5-turbo

colons and their associated textual contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 adversaries

-0.75

æ©

-0.73

 pestic

-0.71

¥ŀ

-0.71

userc

-0.70

senal

-0.69

 breakthrough

-0.67

phabet

-0.67

 ingred

-0.66

 hemor

-0.66

POSITIVE LOGITS

 âĨĳ

0.90

 Interesting

0.88

 Originally

0.85

Show

0.85

Originally

0.73

Wow

0.72

Hmm

0.72

 Assuming

0.72

Nice

0.68

 Surely

0.68

Activations Density 0.073%

text structuring and formatting cues

colons and their associated textual contexts

No Comments

No Known Activations