INDEX

Explanations

instances where a character is talking or thoughts are revealed

oai_token-act-pair · gpt-3.5-turbo

end punctuation marks in sentences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 tremend

-0.79

 favors

-0.66

 subsidized

-0.66

 transact

-0.66

 modernization

-0.64

 abund

-0.63

 prioritize

-0.61

 centralized

-0.61

 biases

-0.60

 incentives

-0.60

POSITIVE LOGITS

↵

1.12

His

1.00

He

1.00

 Pict

0.90

<|endoftext|>

0.88

↵↵

0.88

His

0.82

 Afterwards

0.82

 Picture

0.81

He

0.78

Activations Density 0.288%

instances where a character is talking or thoughts are revealed

end punctuation marks in sentences

No Comments

No Known Activations