INDEX

Explanations

references to radio in various contexts

oai_token-act-pair · gpt-3.5-turbo

mentions of radio-related content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

-0.81

rg

-0.76

rir

-0.73

URES

-0.69

ortium

-0.69

AGES

-0.68

thens

-0.68

 Arbor

-0.67

jamin

-0.65

 Bane

-0.64

POSITIVE LOGITS

 radio

1.04

activity

1.04

actively

1.02

active

0.99

 stations

0.96

 antennas

0.94

 radios

0.91

 antenna

0.91

radio

0.90

 broadcasts

0.88

Activations Density 0.012%

references to radio in various contexts

mentions of radio-related content

No Comments

No Known Activations