INDEX

Explanations

words related to speed or quickness

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "rapid" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

#$#$

-0.76

OULD

-0.75

roma

-0.75

galitarian

-0.73

avering

-0.71

ãģķ

-0.71

ä»£

-0.70

Ñı

-0.69

rights

-0.68

âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦

-0.68

POSITIVE LOGITS

 succession

1.05

aneously

1.02

 paced

0.97

 turnaround

0.93

itude

0.86

ity

0.85

 prototyp

0.82

 influx

0.81

 ascent

0.79

 transit

0.77

Activations Density 0.012%

words related to speed or quickness

occurrences of the word "rapid" in various contexts

No Comments

No Known Activations