INDEX

Explanations

relevant terms during a sports game, such as periods, field calls, late in the quarters, and scores

oai_token-act-pair · gpt-3.5-turbo

specific timelines and scoring events 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 @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

itect

-0.74

anmar

-0.73

channelAvailability

-0.72

chwitz

-0.70

emale

-0.69

icter

-0.67

catentry

-0.66

obbies

-0.66

warts

-0.65

ombies

-0.64

POSITIVE LOGITS

 halftime

1.30

 overtime

0.99

 timeout

0.95

 inning

0.89

 replay

0.85

 kickoff

0.84

 stopp

0.83

 afternoon

0.83

 scoreboard

0.83

 midway

0.83

Activations Density 0.161%

relevant terms during a sports game, such as periods, field calls, late in the quarters, and scores

specific timelines and scoring events in sports contexts

No Comments

No Known Activations