INDEX

Explanations

historical references and citations

oai_token-act-pair · gpt-3.5-turbo

sequences of brackets and characters indicative of references or annotations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

seys

-0.65

 stalls

-0.64

 bills

-0.64

ient

-0.64

orneys

-0.61

ãĤ©

-0.61

çīĪ

-0.61

 Engineers

-0.60

 Bench

-0.60

 Ingredients

-0.60

POSITIVE LOGITS

...]

1.26

âĢ¦]

1.10

Pg

1.02

note

1.02

][

0.92

].

0.90

Footnote

0.89

SOURCE

0.86

][

0.83

etc

0.82

Activations Density 0.017%

historical references and citations

sequences of brackets and characters indicative of references or annotations

No Comments

No Known Activations