INDEX

Explanations

results of actions or events and their consequences

oai_token-act-pair · gpt-3.5-turbo

sentence structures indicating causal relationships and outcomes

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Truth

-0.86

obin

-0.85

venth

-0.81

TPP

-0.77

izont

-0.77

erest

-0.77

agate

-0.76

wcsstore

-0.75

Really

-0.75

ifest

-0.74

POSITIVE LOGITS

 researchers

1.16

 biologists

1.09

 villagers

1.09

 investigators

1.09

 doctors

1.09

 residents

1.08

 inspectors

1.06

 scientists

1.06

 locals

1.06

 surgeons

1.05

Activations Density 0.387%

results of actions or events and their consequences

sentence structures indicating causal relationships and outcomes

No Comments

No Known Activations