INDEX

Explanations

time durations expressed in minutes

oai_token-act-pair · gpt-3.5-turbo

references to duration of time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ename

-0.72

hess

-0.69

ashtra

-0.69

RP

-0.68

using

-0.68

eller

-0.66

BALL

-0.65

responsible

-0.65

ource

-0.65

ignty

-0.64

POSITIVE LOGITS

 intervals

0.87

 increments

0.84

 countdown

0.80

 halftime

0.77

 bursts

0.75

 succession

0.73

 interval

0.73

 turnaround

0.71

 recess

0.71

 siege

0.70

Activations Density 0.051%

time durations expressed in minutes

references to duration of time

No Comments

No Known Activations