INDEX

Explanations

mention of sports competitions and match outcomes

oai_token-act-pair · gpt-3.5-turbo

actions related to competitive confrontations or matches, particularly in sports 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

oun

-0.78

account

-0.77

ridges

-0.76

iscal

-0.75

paralle

-0.73

arse

-0.73

quist

-0.72

aird

-0.71

acea

-0.71

imen

-0.71

POSITIVE LOGITS

him

0.84

 fellow

0.78

RHP

0.76

 opponents

0.73

 captains

0.71

 hordes

0.71

 undefeated

0.70

 unbeaten

0.69

 opponent

0.68

 finalists

0.68

Activations Density 0.099%

mention of sports competitions and match outcomes

actions related to competitive confrontations or matches, particularly in sports contexts

No Comments

No Known Activations