INDEX

Explanations

words related to achievements or accomplishments

oai_token-act-pair · gpt-3.5-turbo

instances of the word "finished."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

tan

-0.85

tar

-0.84

ortium

-0.79

Lear

-0.76

ffer

-0.75

esis

-0.72

enforcement

-0.71

arth

-0.70

ships

-0.70

orb

-0.70

POSITIVE LOGITS

 runner

0.82

 undefeated

0.76

nces

0.73

 unbeaten

0.72

 stuffing

0.71

 Pradesh

0.67

 reading

0.66

ãĤ¤ãĥĪ

0.65

 finish

0.65

 Rounds

0.64

Activations Density 0.017%

words related to achievements or accomplishments

instances of the word "finished."

No Comments

No Known Activations