INDEX

Explanations

terms related to mounting or installing objects in various contexts

oai_token-act-pair · gpt-3.5-turbo

variations of the word "mount" in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Quincy

-0.72

ister

-0.72

nesota

-0.70

uel

-0.69

rx

-0.69

gen

-0.68

owsky

-0.66

glers

-0.66

gone

-0.65

 Wend

-0.65

POSITIVE LOGITS

mounted

1.03

aint

0.99

mount

0.97

 mount

0.77

 mounting

0.75

 mounted

0.75

raint

0.74

ain

0.74

rons

0.74

aine

0.73

Activations Density 0.045%

terms related to mounting or installing objects in various contexts

variations of the word "mount" in different contexts

No Comments

No Known Activations