INDEX

Explanations

sequences containing specific characters, potentially as part of code or other specialized text

oai_token-act-pair · gpt-3.5-turbo

occurrences of a specific character or symbol, likely focusing on a particular character or motif throughout the document

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

geries

-0.94

 distracting

-0.69

 distracted

-0.69

sworth

-0.67

 responders

-0.65

 regul

-0.65

 foreground

-0.64

tee

-0.63

luent

-0.63

raints

-0.62

POSITIVE LOGITS

Ð¸

1.05

ski

0.92

Ð¾

0.92

à¸

0.89

Ð¾Ð

0.88

Ñĥ

0.87

æŃ¦

0.85

âĸĦ

0.85

Ðµ

0.84

Ð°

0.84

Activations Density 0.008%

sequences containing specific characters, potentially as part of code or other specialized text

occurrences of a specific character or symbol, likely focusing on a particular character or motif throughout the document

No Comments

No Known Activations