INDEX

Explanations

terms related to beliefs in one's ability to achieve something

oai_token-act-pair · gpt-3.5-turbo

expressions of capability or possibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ele

-0.67

quartered

-0.66

furt

-0.64

bats

-0.60

agram

-0.59

faces

-0.59

pend

-0.59

 Appears

-0.58

 Coff

-0.58

 Sheet

-0.58

POSITIVE LOGITS

't

1.46

 afford

1.12

berra

1.04

NOT

1.00

 safely

0.95

 withstand

0.93

 survive

0.93

be

0.92

adian

0.90

 replicate

0.90

Activations Density 0.170%

terms related to beliefs in one's ability to achieve something

expressions of capability or possibility

No Comments

No Known Activations