INDEX

Explanations

adjectives related to a steep incline or rise

oai_token-act-pair · gpt-3.5-turbo

descriptive terms related to steepness or difficulty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ulhu

-0.69

blance

-0.69

ignty

-0.68

umbn

-0.66

iuses

-0.66

uter

-0.66

agnetic

-0.65

essage

-0.65

Smy

-0.65

iverpool

-0.64

POSITIVE LOGITS

ened

1.08

ly

1.06

ening

1.05

 slope

1.03

 slopes

1.03

 climb

0.97

 uphill

0.95

 gradient

0.89

le

0.88

 incl

0.88

Activations Density 0.024%

adjectives related to a steep incline or rise

descriptive terms related to steepness or difficulty

No Comments

No Known Activations