INDEX

Explanations

mentions of press conferences

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "press conference."

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

inho

-0.77

 Bram

-0.74

BuyableInstoreAndOnline

-0.71

 Salvador

-0.69

abama

-0.69

 Reconstruction

-0.65

ston

-0.64

ptoms

-0.64

 Parenthood

-0.63

irst

-0.63

POSITIVE LOGITS

urized

1.04

 conference

1.01

conference

1.00

 corps

0.92

 conferences

0.92

ariat

0.87

room

0.84

 Coverage

0.83

wire

0.83

 aggregation

0.82

Activations Density 0.024%

mentions of press conferences

occurrences of the term "press conference."

No Comments

No Known Activations