INDEX

Explanations

names or terms related to individuals, possibly in a news or documentary context

oai_token-act-pair · gpt-3.5-turbo

names or terms associated with individuals and specific titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

soDeliveryDate

-1.09

ishers

-0.85

rol

-0.77

arded

-0.73

roud

-0.71

ween

-0.71

ARD

-0.71

alore

-0.69

NING

-0.68

roleum

-0.67

POSITIVE LOGITS

anguage

1.03

phia

1.00

inia

0.86

nesota

0.81

ication

0.79

dylib

0.77

icity

0.76

ibrary

0.76

iberal

0.76

icate

0.75

Activations Density 0.073%

names or terms related to individuals, possibly in a news or documentary context

names or terms associated with individuals and specific titles

No Comments

No Known Activations