INDEX

Explanations

terms related to constants and numerical values, potentially in the context of various subjects such as biology or mathematics

oai_token-act-pair · gpt-3.5-turbo

references to constants in scientific 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Cosponsors

-0.77

gom

-0.75

ologies

-0.73

CHAT

-0.73

itism

-0.70

geist

-0.68

Crash

-0.68

 Forbidden

-0.68

TN

-0.68

aska

-0.68

POSITIVE LOGITS

uation

0.81

weights

0.80

uates

0.79

iating

0.79

weight

0.78

uated

0.77

cy

0.77

urity

0.77

uating

0.76

isation

0.75

Activations Density 0.027%

terms related to constants and numerical values, potentially in the context of various subjects such as biology or mathematics

references to constants in scientific contexts

No Comments

No Known Activations